From 749059fdbb427b4eebeee939de23a71906f0b7ef Mon Sep 17 00:00:00 2001 From: "(Bit-Mage)" Date: Mon, 14 Oct 2024 17:13:05 +0530 Subject: [PATCH] updates Signed-off-by: (Bit-Mage) --- Content/bib/references.bib | 783 +++++++++++++++++++------------------ 1 file changed, 407 insertions(+), 376 deletions(-) diff --git a/Content/bib/references.bib b/Content/bib/references.bib index d54bcb2..e7715c0 100644 --- a/Content/bib/references.bib +++ b/Content/bib/references.bib @@ -1,165 +1,272 @@ -@misc{sheth_neurosymbolic_2023, - title = {Neurosymbolic {AI} -- {Why}, {What}, and {How}}, - url = {http://arxiv.org/abs/2305.00813}, - doi = {10.48550/arXiv.2305.00813}, - abstract = {Humans interact with the environment using a combination of perception - transforming sensory inputs from their environment into symbols, and cognition - mapping symbols to knowledge about the environment for supporting abstraction, reasoning by analogy, and long-term planning. Human perception-inspired machine perception, in the context of AI, refers to large-scale pattern recognition from raw data using neural networks trained using self-supervised learning objectives such as next-word prediction or object recognition. On the other hand, machine cognition encompasses more complex computations, such as using knowledge of the environment to guide reasoning, analogy, and long-term planning. Humans can also control and explain their cognitive functions. This seems to require the retention of symbolic mappings from perception outputs to knowledge about their environment. For example, humans can follow and explain the guidelines and safety constraints driving their decision-making in safety-critical applications such as healthcare, criminal justice, and autonomous driving. This article introduces the rapidly emerging paradigm of Neurosymbolic AI combines neural networks and knowledge-guided symbolic approaches to create more capable and flexible AI systems. These systems have immense potential to advance both algorithm-level (e.g., abstraction, analogy, reasoning) and application-level (e.g., explainable and safety-constrained decision-making) capabilities of AI systems.}, - urldate = {2024-06-17}, +@inproceedings{foster_cloud_2008, + title = {Cloud {Computing} and {Grid} {Computing} 360-{Degree} {Compared}}, + url = {http://arxiv.org/abs/0901.0131}, + doi = {10.1109/GCE.2008.4738445}, + abstract = {Cloud Computing has become another buzzword after Web 2.0. However, there are dozens of different definitions for Cloud Computing and there seems to be no consensus on what a Cloud is. On the other hand, Cloud Computing is not a completely new concept; it has intricate connection to the relatively new but thirteen-year established Grid Computing paradigm, and other relevant technologies such as utility computing, cluster computing, and distributed systems in general. This paper strives to compare and contrast Cloud Computing with Grid Computing from various angles and give insights into the essential characteristics of both.}, + urldate = {2024-09-09}, + booktitle = {2008 {Grid} {Computing} {Environments} {Workshop}}, + author = {Foster, Ian and Zhao, Yong and Raicu, Ioan and Lu, Shiyong}, + month = nov, + year = {2008}, + keywords = {A.1, and Cluster Computing, C.2.4, Computer Science - Distributed, Parallel}, + pages = {1--10}, + annote = {arXiv:0901.0131 [cs]}, +} + +@misc{yin_goagent_2024, + title = {Gödel {Agent}: {A} {Self}-{Referential} {Agent} {Framework} for {Recursive} {Self}-{Improvement}}, + shorttitle = {Gödel {Agent}}, + url = {http://arxiv.org/abs/2410.04444}, + doi = {10.48550/arXiv.2410.04444}, + abstract = {The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined meta-learning frameworks, cannot search the whole agent design space due to the restriction of human-designed components, and thus might miss the globally optimal agent design. In this paper, we introduce G{\textbackslash}"odel Agent, a self-evolving framework inspired by the G{\textbackslash}"odel machine, enabling agents to recursively improve themselves without relying on predefined routines or fixed optimization algorithms. G{\textbackslash}"odel Agent leverages LLMs to dynamically modify its own logic and behavior, guided solely by high-level objectives through prompting. Experimental results on mathematical reasoning and complex agent tasks demonstrate that implementation of G{\textbackslash}"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.}, + urldate = {2024-10-14}, publisher = {arXiv}, - author = {Sheth, Amit and Roy, Kaushik and Gaur, Manas}, - month = may, - year = {2023}, - note = {arXiv:2305.00813 [cs]}, + author = {Yin, Xunjian and Wang, Xinyi and Pan, Liangming and Wan, Xiaojun and Wang, William Yang}, + month = oct, + year = {2024}, + note = {arXiv:2410.04444}, keywords = {Computer Science - Artificial Intelligence}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/XKHCL4IW/Sheth et al. - 2023 - Neurosymbolic AI -- Why, What, and How.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/JWNHUYEJ/2305.html:text/html}, + file = {Preprint PDF:/home/rp152k/Zotero/storage/9HLKV59J/Yin et al. - 2024 - Gödel Agent A Self-Referential Agent Framework for Recursive Self-Improvement.pdf:application/pdf;Snapshot:/home/rp152k/Zotero/storage/KUJG8AGJ/2410.html:text/html}, } -@misc{garcez_neurosymbolic_2020, - title = {Neurosymbolic {AI}: {The} 3rd {Wave}}, - shorttitle = {Neurosymbolic {AI}}, - url = {http://arxiv.org/abs/2012.05876}, - doi = {10.48550/arXiv.2012.05876}, - abstract = {Current advances in Artificial Intelligence (AI) and Machine Learning (ML) have achieved unprecedented impact across research communities and industry. Nevertheless, concerns about trust, safety, interpretability and accountability of AI were raised by influential thinkers. Many have identified the need for well-founded knowledge representation and reasoning to be integrated with deep learning and for sound explainability. Neural-symbolic computing has been an active area of research for many years seeking to bring together robust learning in neural networks with reasoning and explainability via symbolic representations for network models. In this paper, we relate recent and early research results in neurosymbolic AI with the objective of identifying the key ingredients of the next wave of AI systems. We focus on research that integrates in a principled way neural network-based learning with symbolic knowledge representation and logical reasoning. The insights provided by 20 years of neural-symbolic computing are shown to shed new light onto the increasingly prominent role of trust, safety, interpretability and accountability of AI. We also identify promising directions and challenges for the next decade of AI research from the perspective of neural-symbolic systems.}, - urldate = {2024-06-17}, +@article{noauthor_hyperspace_nodate, + title = {Hyperspace: {A} {Peer}-to-{Peer} {Artificial} {Intelligence} {Network}}, + language = {en}, + file = {PDF:/home/rp152k/Zotero/storage/6URQ2X79/Hyperspace A Peer-to-Peer Artificial Intelligence Network.pdf:application/pdf}, +} + +@misc{lertpongrujikorn_object_2024, + title = {Object as a {Service}: {Simplifying} {Cloud}-{Native} {Development} through {Serverless} {Object} {Abstraction}}, + shorttitle = {Object as a {Service}}, + url = {http://arxiv.org/abs/2408.04898}, + doi = {10.48550/arXiv.2408.04898}, + abstract = {The function-as-a-service (FaaS) paradigm is envisioned as the next generation of cloud computing systems that mitigate the burden for cloud-native application developers by abstracting them from cloud resource management. However, it does not deal with the application data aspects. As such, developers have to intervene and undergo the burden of managing the application data, often via separate cloud storage services. To further streamline cloud-native application development, in this work, we propose a new paradigm, known as Object as a Service (OaaS) that encapsulates application data and functions into the cloud object abstraction. OaaS relieves developers from resource and data management burden while offering built-in optimization features. Inspired by OOP, OaaS incorporates access modifiers and inheritance into the serverless paradigm that: (a) prevents developers from compromising the system via accidentally accessing underlying data; and (b) enables software reuse in cloud-native application development. Furthermore, OaaS natively supports dataflow semantics. It enables developers to define function workflows while transparently handling data navigation, synchronization, and parallelism issues. To establish the OaaS paradigm, we develop a platform named Oparaca that offers state abstraction for structured and unstructured data with consistency and fault-tolerant guarantees. We evaluated Oparaca under real-world settings against state-of-the-art platforms with respect to the imposed overhead, scalability, and ease of use. The results demonstrate that the object abstraction provided by OaaS can streamline flexible and scalable cloud-native application development with an insignificant overhead on the underlying serverless system.}, + urldate = {2024-09-09}, publisher = {arXiv}, - author = {Garcez, Artur d'Avila and Lamb, Luis C.}, - month = dec, - year = {2020}, - note = {arXiv:2012.05876 [cs]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, I.2.4, I.2.6}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/62RGF8PB/Garcez and Lamb - 2020 - Neurosymbolic AI The 3rd Wave.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/3QTEEPKH/2012.html:text/html}, + author = {Lertpongrujikorn, Pawissanutt and Salehi, Mohsen Amini}, + month = aug, + year = {2024}, + note = {arXiv:2408.04898 [cs]}, + keywords = {Computer Science - Software Engineering, Computer Science - Operating Systems, Computer Science - Distributed, Parallel, and Cluster Computing}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/PEPQE9BN/Lertpongrujikorn and Salehi - 2024 - Object as a Service Simplifying Cloud-Native Deve.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/3RWB5Q69/2408.html:text/html}, } -@article{hitzler_neural-symbolic_2020, - title = {Neural-symbolic integration and the {Semantic} {Web}}, - volume = {11}, - issn = {22104968, 15700844}, - url = {https://www.medra.org/servlet/aliasResolver?alias=iospress&doi=10.3233/SW-190368}, - doi = {10.3233/SW-190368}, - language = {en}, - number = {1}, - urldate = {2024-06-17}, - journal = {Semantic Web}, - author = {Hitzler, Pascal and Bianchi, Federico and Ebrahimi, Monireh and Sarker, Md Kamruzzaman}, - editor = {Janowicz, Krzysztof}, - month = jan, - year = {2020}, - pages = {3--11}, - file = {Hitzler et al. - 2020 - Neural-symbolic integration and the Semantic Web.pdf:/home/rp152k/Zotero/storage/TXQTYC6N/Hitzler et al. - 2020 - Neural-symbolic integration and the Semantic Web.pdf:application/pdf}, +@misc{jonas_cloud_2019, + title = {Cloud {Programming} {Simplified}: {A} {Berkeley} {View} on {Serverless} {Computing}}, + shorttitle = {Cloud {Programming} {Simplified}}, + url = {http://arxiv.org/abs/1902.03383}, + doi = {10.48550/arXiv.1902.03383}, + abstract = {Serverless cloud computing handles virtually all the system administration operations needed to make it easier for programmers to use the cloud. It provides an interface that greatly simplifies cloud programming, and represents an evolution that parallels the transition from assembly language to high-level programming languages. This paper gives a quick history of cloud computing, including an accounting of the predictions of the 2009 Berkeley View of Cloud Computing paper, explains the motivation for serverless computing, describes applications that stretch the current limits of serverless, and then lists obstacles and research opportunities required for serverless computing to fulfill its full potential. Just as the 2009 paper identified challenges for the cloud and predicted they would be addressed and that cloud use would accelerate, we predict these issues are solvable and that serverless computing will grow to dominate the future of cloud computing.}, + urldate = {2024-09-09}, + publisher = {arXiv}, + author = {Jonas, Eric and Schleier-Smith, Johann and Sreekanti, Vikram and Tsai, Chia-Che and Khandelwal, Anurag and Pu, Qifan and Shankar, Vaishaal and Carreira, Joao and Krauth, Karl and Yadwadkar, Neeraja and Gonzalez, Joseph E. and Popa, Raluca Ada and Stoica, Ion and Patterson, David A.}, + month = feb, + year = {2019}, + note = {arXiv:1902.03383 [cs]}, + keywords = {Computer Science - Operating Systems}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/5U42GVFM/Jonas et al. - 2019 - Cloud Programming Simplified A Berkeley View on S.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/4XBHYBH3/1902.html:text/html}, } -@misc{bottou_machine_2011, - title = {From {Machine} {Learning} to {Machine} {Reasoning}}, - url = {http://arxiv.org/abs/1102.1808}, - doi = {10.48550/arXiv.1102.1808}, - abstract = {A plausible definition of "reasoning" could be "algebraically manipulating previously acquired knowledge in order to answer a new question". This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical character recognition system by first training a character segmenter, an isolated character recognizer, and a language model, using appropriate labeled training sets. Adequately concatenating these modules and fine tuning the resulting system can be viewed as an algebraic operation in a space of models. The resulting model answers a new question, that is, converting the image of a text page into a computer readable text. This observation suggests a conceptual continuity between algebraically rich inference systems, such as logical or probabilistic inference, and simple manipulations, such as the mere concatenation of trainable learning systems. Therefore, instead of trying to bridge the gap between machine learning systems and sophisticated "all-purpose" inference mechanisms, we can instead algebraically enrich the set of manipulations applicable to training systems, and build reasoning capabilities from the ground up.}, - urldate = {2024-06-17}, +@misc{varghese_cloud_2019, + title = {Cloud {Futurology}}, + url = {http://arxiv.org/abs/1902.03656}, + doi = {10.48550/arXiv.1902.03656}, + abstract = {The Cloud has become integral to most Internet-based applications and user gadgets. This article provides a brief history of the Cloud and presents a researcher's view of the prospects for innovating at the infrastructure, middleware, and application and delivery levels of the already crowded Cloud computing stack.}, + urldate = {2024-09-09}, publisher = {arXiv}, - author = {Bottou, Leon}, + author = {Varghese, Blesson and Leitner, Philipp and Ray, Suprio and Chard, Kyle and Barker, Adam and Elkhatib, Yehia and Herry, Herry and Hong, Cheol-Ho and Singer, Jeremy and Tso, Fung Po and Yoneki, Eiko and Zhani, Mohamed-Faten}, month = feb, - year = {2011}, - note = {arXiv:1102.1808 [cs]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/MJ6VVSW2/Bottou - 2011 - From Machine Learning to Machine Reasoning.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/GYZQ2VD2/1102.html:text/html}, + year = {2019}, + note = {arXiv:1902.03656 [cs]}, + keywords = {Computer Science - Distributed, Parallel, and Cluster Computing}, + annote = {Comment: Accepted to IEEE Computer, 2019}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/3SFQ82BX/Varghese et al. - 2019 - Cloud Futurology.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/UGM8DRHY/1902.html:text/html}, } -@misc{de_raedt_statistical_2020, - title = {From {Statistical} {Relational} to {Neuro}-{Symbolic} {Artificial} {Intelligence}}, - url = {http://arxiv.org/abs/2003.08316}, - doi = {10.48550/arXiv.2003.08316}, - abstract = {Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these two fields. These cannot only be used to characterize and position neuro-symbolic artificial intelligence approaches but also to identify a number of directions for further research.}, - urldate = {2024-06-17}, +@misc{ramadan_role_2024, + title = {The {Role} of {Artificial} {Intelligence} and {Machine} {Learning} in {Software} {Testing}}, + url = {http://arxiv.org/abs/2409.02693}, + doi = {10.48550/arXiv.2409.02693}, + abstract = {Artificial Intelligence (AI) and Machine Learning (ML) have significantly impacted various industries, including software development. Software testing, a crucial part of the software development lifecycle (SDLC), ensures the quality and reliability of software products. Traditionally, software testing has been a labor-intensive process requiring significant manual effort. However, the advent of AI and ML has transformed this landscape by introducing automation and intelligent decision-making capabilities. AI and ML technologies enhance the efficiency and effectiveness of software testing by automating complex tasks such as test case generation, test execution, and result analysis. These technologies reduce the time required for testing and improve the accuracy of defect detection, ultimately leading to higher quality software. AI can predict potential areas of failure by analyzing historical data and identifying patterns, which allows for more targeted and efficient testing. This paper explores the role of AI and ML in software testing by reviewing existing literature, analyzing current tools and techniques, and presenting case studies that demonstrate the practical benefits of these technologies. The literature review provides a comprehensive overview of the advancements in AI and ML applications in software testing, highlighting key methodologies and findings from various studies. The analysis of current tools showcases the capabilities of popular AI-driven testing tools such as Eggplant AI, Test.ai, Selenium, Appvance, Applitools Eyes, Katalon Studio, and Tricentis Tosca, each offering unique features and advantages. Case studies included in this paper illustrate real-world applications of AI and ML in software testing, showing significant improvements in testing efficiency, accuracy, and overall software quality.}, + urldate = {2024-09-09}, publisher = {arXiv}, - author = {De Raedt, Luc and Dumančić, Sebastijan and Manhaeve, Robin and Marra, Giuseppe}, - month = mar, - year = {2020}, - note = {arXiv:2003.08316 [cs]}, - keywords = {Computer Science - Artificial Intelligence}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/U4FGFF77/De Raedt et al. - 2020 - From Statistical Relational to Neuro-Symbolic Arti.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/8IVPLMHU/2003.html:text/html}, + author = {Ramadan, Ahmed and Yasin, Husam and Pektas, Burhan}, + month = sep, + year = {2024}, + note = {arXiv:2409.02693 [cs]}, + keywords = {Computer Science - Artificial Intelligence, Computer Science - Software Engineering}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/FGVSTR8X/Ramadan et al. - 2024 - The Role of Artificial Intelligence and Machine Le.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/73QW5ILT/2409.html:text/html}, } -@misc{noauthor_neuro-symbolic_nodate, - title = {Neuro-{Symbolic} {Artificial} {Intelligence} - workshops}, - url = {https://people.cs.ksu.edu/~hitzler/nesy/}, - urldate = {2024-06-17}, - file = {Neuro-Symbolic Artificial Intelligence:/home/rp152k/Zotero/storage/63DNPJFW/nesy.html:text/html}, +@misc{astekin_comparative_2024, + title = {A {Comparative} {Study} on {Large} {Language} {Models} for {Log} {Parsing}}, + url = {http://arxiv.org/abs/2409.02474}, + doi = {10.1145/3674805.3686684}, + abstract = {Background: Log messages provide valuable information about the status of software systems. This information is provided in an unstructured fashion and automated approaches are applied to extract relevant parameters. To ease this process, log parsing can be applied, which transforms log messages into structured log templates. Recent advances in language models have led to several studies that apply ChatGPT to the task of log parsing with promising results. However, the performance of other state-of-the-art large language models (LLMs) on the log parsing task remains unclear. Aims: In this study, we investigate the current capability of state-of-the-art LLMs to perform log parsing. Method: We select six recent LLMs, including both paid proprietary (GPT-3.5, Claude 2.1) and four free-to-use open models, and compare their performance on system logs obtained from a selection of mature open-source projects. We design two different prompting approaches and apply the LLMs on 1, 354 log templates across 16 different projects. We evaluate their effectiveness, in the number of correctly identified templates, and the syntactic similarity between the generated templates and the ground truth. Results: We found that free-to-use models are able to compete with paid models, with CodeLlama extracting 10\% more log templates correctly than GPT-3.5. Moreover, we provide qualitative insights into the usability of language models (e.g., how easy it is to use their responses). Conclusions: Our results reveal that some of the smaller, free-to-use LLMs can considerably assist log parsing compared to their paid proprietary competitors, especially code-specialized models.}, + urldate = {2024-09-09}, + author = {Astekin, Merve and Hort, Max and Moonen, Leon}, + month = sep, + year = {2024}, + note = {arXiv:2409.02474 [cs]}, + keywords = {Computer Science - Computation and Language, Computer Science - Software Engineering}, + annote = {Comment: Accepted for publication in the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM '24)}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/2QVCQWHG/Astekin et al. - 2024 - A Comparative Study on Large Language Models for L.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/U4ZMLUQB/2409.html:text/html}, } -@misc{lamb_graph_2021, - title = {Graph {Neural} {Networks} {Meet} {Neural}-{Symbolic} {Computing}: {A} {Survey} and {Perspective}}, - shorttitle = {Graph {Neural} {Networks} {Meet} {Neural}-{Symbolic} {Computing}}, - url = {http://arxiv.org/abs/2003.00330}, - doi = {10.48550/arXiv.2003.00330}, - abstract = {Neural-symbolic computing has now become the subject of interest of both academic and industry research laboratories. Graph Neural Networks (GNN) have been widely used in relational and symbolic domains, with widespread application of GNNs in combinatorial optimization, constraint satisfaction, relational reasoning and other scientific domains. The need for improved explainability, interpretability and trust of AI systems in general demands principled methodologies, as suggested by neural-symbolic computing. In this paper, we review the state-of-the-art on the use of GNNs as a model of neural-symbolic computing. This includes the application of GNNs in several domains as well as its relationship to current developments in neural-symbolic computing.}, - urldate = {2024-06-17}, - publisher = {arXiv}, - author = {Lamb, Luis C. and Garcez, Artur and Gori, Marco and Prates, Marcelo and Avelar, Pedro and Vardi, Moshe}, - month = jun, - year = {2021}, - note = {arXiv:2003.00330 [cs]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Logic in Computer Science}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/2SP4FU4E/Lamb et al. - 2021 - Graph Neural Networks Meet Neural-Symbolic Computi.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/URE2YKP9/2003.html:text/html}, +@misc{guo_deepseek-coder_2024, + title = {{DeepSeek}-{Coder}: {When} the {Large} {Language} {Model} {Meets} {Programming} -- {The} {Rise} of {Code} {Intelligence}}, + shorttitle = {{DeepSeek}-{Coder}}, + url = {https://arxiv.org/abs/2401.14196v2}, + abstract = {The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extensive research and development. To address this, we introduce the DeepSeek-Coder series, a range of open-source code models with sizes from 1.3B to 33B, trained from scratch on 2 trillion tokens. These models are pre-trained on a high-quality project-level code corpus and employ a fill-in-the-blank task with a 16K window to enhance code generation and infilling. Our extensive evaluations demonstrate that DeepSeek-Coder not only achieves state-of-the-art performance among open-source code models across multiple benchmarks but also surpasses existing closed-source models like Codex and GPT-3.5. Furthermore, DeepSeek-Coder models are under a permissive license that allows for both research and unrestricted commercial use.}, + language = {en}, + urldate = {2024-09-08}, + journal = {arXiv.org}, + author = {Guo, Daya and Zhu, Qihao and Yang, Dejian and Xie, Zhenda and Dong, Kai and Zhang, Wentao and Chen, Guanting and Bi, Xiao and Wu, Y. and Li, Y. K. and Luo, Fuli and Xiong, Yingfei and Liang, Wenfeng}, + month = jan, + year = {2024}, + file = {Full Text PDF:/home/rp152k/Zotero/storage/N729SIHI/Guo et al. - 2024 - DeepSeek-Coder When the Large Language Model Meet.pdf:application/pdf}, } -@misc{battaglia_relational_2018, - title = {Relational inductive biases, deep learning, and graph networks}, - url = {http://arxiv.org/abs/1806.01261}, - doi = {10.48550/arXiv.1806.01261}, - abstract = {Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between "hand-engineering" and "end-to-end" learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.}, - urldate = {2024-06-17}, +@misc{mersha_explainable_2024, + title = {Explainable {Artificial} {Intelligence}: {A} {Survey} of {Needs}, {Techniques}, {Applications}, and {Future} {Direction}}, + shorttitle = {Explainable {Artificial} {Intelligence}}, + url = {https://arxiv.org/abs/2409.00265v1}, + abstract = {Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these challenges by providing explanations for how these models make decisions and predictions, ensuring transparency, accountability, and fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, and the scope of XAI techniques. However, there remains a gap in the literature as there are no comprehensive reviews that delve into the detailed mathematical representations, design methodologies of XAI models, and other associated aspects. This paper provides a comprehensive literature review encompassing common terminologies and definitions, the need for XAI, beneficiaries of XAI, a taxonomy of XAI methods, and the application of XAI methods in different application areas. The survey is aimed at XAI researchers, XAI practitioners, AI model developers, and XAI beneficiaries who are interested in enhancing the trustworthiness, transparency, accountability, and fairness of their AI models.}, + language = {en}, + urldate = {2024-09-08}, + journal = {arXiv.org}, + author = {Mersha, Melkamu and Lam, Khang and Wood, Joseph and AlShami, Ali and Kalita, Jugal}, + month = aug, + year = {2024}, + doi = {10.1016/j.neucom.2024.128111}, + file = {Full Text PDF:/home/rp152k/Zotero/storage/XNX3MQB8/Mersha et al. - 2024 - Explainable Artificial Intelligence A Survey of N.pdf:application/pdf}, +} + +@misc{zhang_no_2024, + title = {No {Man} is an {Island}: {Towards} {Fully} {Automatic} {Programming} by {Code} {Search}, {Code} {Generation} and {Program} {Repair}}, + shorttitle = {No {Man} is an {Island}}, + url = {https://arxiv.org/abs/2409.03267v1}, + abstract = {Automatic programming attempts to minimize human intervention in the generation of executable code, and has been a long-standing challenge in the software engineering community. To advance automatic programming, researchers are focusing on three primary directions: (1) code search that reuses existing code snippets from external databases; (2) code generation that produces new code snippets from natural language; and (3) program repair that refines existing code snippets by fixing detected bugs. Despite significant advancements, the effectiveness of state-of-the-art techniques is still limited, such as the usability of searched code and the correctness of generated code. Motivated by the real-world programming process, where developers usually use various external tools to aid their coding processes, such as code search engines and code testing tools, in this work, we propose {\textbackslash}toolname\{\}, an automatic programming framework that leverages recent large language models (LLMs) to integrate the three research areas to address their inherent limitations. In particular, our framework first leverages different code search strategies to retrieve similar code snippets, which are then used to further guide the code generation process of LLMs. Our framework further validates the quality of generated code by compilers and test cases, and constructs repair prompts to query LLMs for generating correct patches. We conduct preliminary experiments to demonstrate the potential of our framework, {\textbackslash}eg helping CodeLlama solve 267 programming problems with an improvement of 62.53{\textbackslash}\%. As a generic framework, {\textbackslash}toolname\{\} can integrate various code search, generation, and repair tools, combining these three research areas together for the first time. More importantly, it demonstrates the potential of using traditional SE tools to enhance the usability of LLMs in automatic programming.}, + language = {en}, + urldate = {2024-09-08}, + journal = {arXiv.org}, + author = {Zhang, Quanjun and Fang, Chunrong and Shang, Ye and Zhang, Tongke and Yu, Shengcheng and Chen, Zhenyu}, + month = sep, + year = {2024}, + file = {Full Text PDF:/home/rp152k/Zotero/storage/Y746HTV6/Zhang et al. - 2024 - No Man is an Island Towards Fully Automatic Progr.pdf:application/pdf}, +} + +@misc{cvetkovic_dirigent_2024, + title = {Dirigent: {Lightweight} {Serverless} {Orchestration}}, + shorttitle = {Dirigent}, + url = {https://arxiv.org/abs/2404.16393v1}, + abstract = {While Function as a Service (FaaS) platforms can initialize function sandboxes on worker nodes in 10-100s of milliseconds, the latency to schedule functions in real FaaS clusters can be orders of magnitude higher. We find that the current approach of building FaaS cluster managers on top of legacy orchestration systems like Kubernetes leads to high scheduling delay at high sandbox churn, which is typical in FaaS clusters. While generic cluster managers use hierarchical abstractions and multiple internal components to manage and reconcile state with frequent persistent updates, this becomes a bottleneck for FaaS, where cluster state frequently changes as sandboxes are created on the critical path of requests. Based on our root cause analysis of performance issues in existing FaaS cluster managers, we propose Dirigent, a clean-slate system architecture for FaaS orchestration with three key principles. First, Dirigent optimizes internal cluster manager abstractions to simplify state management. Second, it eliminates persistent state updates on the critical path of function invocations, leveraging the fact that FaaS abstracts sandboxes from users to relax exact state reconstruction guarantees. Finally, Dirigent runs monolithic control and data planes to minimize internal communication overheads and maximize throughput. We compare Dirigent to state-of-the-art FaaS platforms and show that Dirigent reduces 99th percentile per-function scheduling latency for a production workload by 2.79x compared to AWS Lambda and can spin up 2500 sandboxes per second at low latency, which is 1250x more than with Knative.}, + language = {en}, + urldate = {2024-09-07}, + journal = {arXiv.org}, + author = {Cvetković, Lazar and Costa, François and Djokic, Mihajlo and Friedman, Michal and Klimovic, Ana}, + month = apr, + year = {2024}, + file = {Full Text PDF:/home/rp152k/Zotero/storage/YXK2X5XS/Cvetković et al. - 2024 - Dirigent Lightweight Serverless Orchestration.pdf:application/pdf}, +} + +@misc{thijsman_trusting_2024, + title = {Trusting the {Cloud}-{Native} {Edge}: {Remotely} {Attested} {Kubernetes} {Workers}}, + shorttitle = {Trusting the {Cloud}-{Native} {Edge}}, + url = {http://arxiv.org/abs/2405.10131}, + doi = {10.48550/arXiv.2405.10131}, + abstract = {A Kubernetes cluster typically consists of trusted nodes, running within the confines of a physically secure datacenter. With recent advances in edge orchestration, this is no longer the case. This poses a new challenge: how can we trust a device that an attacker has physical access to? This paper presents an architecture and open-source implementation that securely enrolls edge devices as trusted Kubernetes worker nodes. By providing boot attestation rooted in a hardware Trusted Platform Module, a strong base of trust is provided. A new custom controller directs a modified version of Keylime to cross the cloud-edge gap and securely deliver unique cluster credentials required to enroll an edge worker. The controller dynamically grants and revokes these credentials based on attestation events, preventing a possibly compromised node from accessing sensitive cluster resources. We provide both a qualitative and a quantitative evaluation of the architecture. The qualitative scenarios prove its ability to attest and enroll an edge device with role-based access control (RBAC) permissions that dynamically adjust to attestation events. The quantitative evaluation reflects an average of 10.28 seconds delay incurred on the startup time of the edge node due to attestation for a total average enrollment time of 20.91 seconds. The presented architecture thus provides a strong base of trust, securing a physically exposed edge device and paving the way for a robust and resilient edge computing ecosystem.}, + urldate = {2024-09-07}, publisher = {arXiv}, - author = {Battaglia, Peter W. and Hamrick, Jessica B. and Bapst, Victor and Sanchez-Gonzalez, Alvaro and Zambaldi, Vinicius and Malinowski, Mateusz and Tacchetti, Andrea and Raposo, David and Santoro, Adam and Faulkner, Ryan and Gulcehre, Caglar and Song, Francis and Ballard, Andrew and Gilmer, Justin and Dahl, George and Vaswani, Ashish and Allen, Kelsey and Nash, Charles and Langston, Victoria and Dyer, Chris and Heess, Nicolas and Wierstra, Daan and Kohli, Pushmeet and Botvinick, Matt and Vinyals, Oriol and Li, Yujia and Pascanu, Razvan}, - month = oct, - year = {2018}, - note = {arXiv:1806.01261 [cs, stat]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Statistics - Machine Learning}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/S6TRQ9KR/Battaglia et al. - 2018 - Relational inductive biases, deep learning, and gr.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/JRHFDMQ4/1806.html:text/html}, + author = {Thijsman, Jordi and Sebrechts, Merlijn and De Turck, Filip and Volckaert, Bruno}, + month = may, + year = {2024}, + note = {arXiv:2405.10131 [cs]}, + keywords = {Computer Science - Cryptography and Security}, + annote = {Comment: Pre-print of article accepted to IEEE ICCCN 2024}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/FWNQPCGP/Thijsman et al. - 2024 - Trusting the Cloud-Native Edge Remotely Attested .pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/5PCRPWUA/2405.html:text/html}, } -@misc{yi_neural-symbolic_2019, - title = {Neural-{Symbolic} {VQA}: {Disentangling} {Reasoning} from {Vision} and {Language} {Understanding}}, - shorttitle = {Neural-{Symbolic} {VQA}}, - url = {http://arxiv.org/abs/1810.02338}, - doi = {10.48550/arXiv.1810.02338}, - abstract = {We marry two powerful ideas: deep representation learning for visual recognition and language understanding, and symbolic program execution for reasoning. Our neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question. It then executes the program on the scene representation to obtain an answer. Incorporating symbolic structure as prior knowledge offers three unique advantages. First, executing programs on a symbolic space is more robust to long program traces; our model can solve complex reasoning tasks better, achieving an accuracy of 99.8\% on the CLEVR dataset. Second, the model is more data- and memory-efficient: it performs well after learning on a small number of training data; it can also encode an image into a compact representation, requiring less storage than existing methods for offline question answering. Third, symbolic program execution offers full transparency to the reasoning process; we are thus able to interpret and diagnose each execution step.}, - urldate = {2024-06-17}, +@misc{de_palma_funless_2024, + title = {{FunLess}: {Functions}-as-a-{Service} for {Private} {Edge} {Cloud} {Systems}}, + shorttitle = {{FunLess}}, + url = {http://arxiv.org/abs/2405.21009}, + doi = {10.48550/arXiv.2405.21009}, + abstract = {We present FunLess, a Function-as-a-Service (FaaS) platform tailored for the private edge cloud system. FunLess responds to recent trends that advocate for extending the coverage of serverless computing to private edge cloud systems and enhancing latency, security, and privacy while improving resource usage. Unlike existing solutions that rely on containers for function invocation, FunLess leverages WebAssembly (Wasm) as its runtime environment. Wasm's lightweight, sandboxed runtime is crucial to have functions run on constrained devices at the edge. Moreover, the advantages of using Wasm in FunLess include a consistent development and deployment environment for users and function portability (write once, run everywhere) We validate FunLess under different deployment scenarios, characterised by the presence/absence of constrained-resource devices (Raspberry Pi 3B+) and the (in)accessibility of container orchestration technologies - Kubernetes. We compare FunLess with three production-ready, widely adopted open-source FaaS platforms - OpenFaaS, Fission, and Knative. Our benchmarks confirm that FunLess is a proper solution for FaaS private edge cloud systems since it achieves performance comparable to the considered FaaS alternatives while it is the only fully-deployable alternative on constrained-resource devices, thanks to its small memory footprint.}, + urldate = {2024-09-07}, publisher = {arXiv}, - author = {Yi, Kexin and Wu, Jiajun and Gan, Chuang and Torralba, Antonio and Kohli, Pushmeet and Tenenbaum, Joshua B.}, - month = jan, - year = {2019}, - note = {arXiv:1810.02338 [cs]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/WQ8SJ528/Yi et al. - 2019 - Neural-Symbolic VQA Disentangling Reasoning from .pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/9CIDLP4A/1810.html:text/html}, + author = {De Palma, Giuseppe and Giallorenzo, Saverio and Mauro, Jacopo and Trentin, Matteo and Zavattaro, Gianluigi}, + month = may, + year = {2024}, + note = {arXiv:2405.21009 [cs]}, + keywords = {Computer Science - Distributed, Parallel, and Cluster Computing}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/5QG9ZBAW/De Palma et al. - 2024 - FunLess Functions-as-a-Service for Private Edge C.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/2LVP2YTR/2405.html:text/html}, } -@misc{vaswani_attention_2023, - title = {Attention {Is} {All} {You} {Need}}, - url = {http://arxiv.org/abs/1706.03762}, - doi = {10.48550/arXiv.1706.03762}, - abstract = {The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.}, - urldate = {2024-06-19}, +@article{gupta_columnar_2021, + title = {Columnar storage and list-based processing for graph database management systems}, + volume = {14}, + issn = {2150-8097}, + url = {https://dl.acm.org/doi/10.14778/3476249.3476297}, + doi = {10.14778/3476249.3476297}, + abstract = {We revisit column-oriented storage and query processing techniques in the context of contemporary graph database management systems (GDBMSs). Similar to column-oriented RDBMSs, GDBMSs support read-heavy analytical workloads that however have fundamentally different data access patterns than traditional analytical workloads. We first derive a set of desiderata for optimizing storage and query processors of GDBMS based on their access patterns. We then present the design of columnar storage, compression, and query processing techniques based on these desiderata. In addition to showing direct integration of existing techniques from columnar RDBMSs, we also propose novel ones that are optimized for GDBMSs. These include a novel list-based query processor, which avoids expensive data copies of traditional block-based processors under many-to-many joins, a new data structure we call singleindexed edge property pages and an accompanying edge ID scheme, and a new application of Jacobson’s bit vector index for compressing NULL values and empty lists. We integrated our techniques into the GraphflowDB in-memory GDBMS. Through extensive experiments, we demonstrate the scalability and query performance benefits of our techniques.}, + language = {en}, + number = {11}, + urldate = {2024-09-07}, + journal = {Proceedings of the VLDB Endowment}, + author = {Gupta, Pranjal and Mhedhbi, Amine and Salihoglu, Semih}, + month = jul, + year = {2021}, + pages = {2491--2504}, + file = {Gupta et al. - 2021 - Columnar storage and list-based processing for gra.pdf:/home/rp152k/Zotero/storage/EAE8LYB9/Gupta et al. - 2021 - Columnar storage and list-based processing for gra.pdf:application/pdf}, +} + +@misc{ueno_migrating_2024, + title = {Migrating {Existing} {Container} {Workload} to {Kubernetes} -- {LLM} {Based} {Approach} and {Evaluation}}, + url = {http://arxiv.org/abs/2408.11428}, + doi = {10.48550/arXiv.2408.11428}, + abstract = {Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One approach employs large language models (LLMs) to assist developers in generating Kubernetes manifests; however it is currently impossible to determine whether the output satisfies given specifications and is comprehensible. In this study, we proposed a benchmarking method for evaluating the effectiveness of LLMs in synthesizing manifests, using the Compose specification -- a standard widely adopted by application developers -- as input. The proposed benchmarking method revealed that LLMs generally produce accurate results that compensate for simple specification gaps. However, we also observed that inline comments for readability were often omitted, and completion accuracy was low for atypical inputs with unclear intentions.}, + urldate = {2024-08-23}, publisher = {arXiv}, - author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Lukasz and Polosukhin, Illia}, + author = {Ueno, Masaru and Uchiumi, Tetsuya}, month = aug, - year = {2023}, - note = {arXiv:1706.03762 [cs]}, - keywords = {Computer Science - Machine Learning, Computer Science - Computation and Language}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/335MFALG/Vaswani et al. - 2023 - Attention Is All You Need.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/KR7F69YM/1706.html:text/html}, + year = {2024}, + note = {arXiv:2408.11428 [cs]}, + keywords = {Computer Science - Software Engineering}, + annote = {Comment: submitted to ICSME 2024 Industry Track}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/3M5HNIV6/Ueno and Uchiumi - 2024 - Migrating Existing Container Workload to Kubernete.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/ATBNY8SK/2408.html:text/html}, } -@misc{zhang_new_2023, - title = {A {New} {Information} {Theory} of {Certainty} for {Machine} {Learning}}, - url = {http://arxiv.org/abs/2304.12833}, - doi = {10.48550/arXiv.2304.12833}, - abstract = {Claude Shannon coined entropy to quantify the uncertainty of a random distribution for communication coding theory. We observe that the uncertainty nature of entropy also limits its direct usage in mathematical modeling. Therefore we propose a new concept troenpy,as the canonical dual of entropy, to quantify the certainty of the underlying distribution. We demonstrate two applications in machine learning. The first is for the classical document classification, we develop a troenpy based weighting scheme to leverage the document class label. The second is a self-troenpy weighting scheme for sequential data and show that it can be easily included in neural network based language models and achieve dramatic perplexity reduction. We also define quantum troenpy as the dual of the Von Neumann entropy to quantify the certainty of quantum systems.}, - urldate = {2024-07-07}, +@misc{kalwarowskyj_parallel_2023, + title = {Parallel {Neural} {Networks} in {Golang}}, + url = {http://arxiv.org/abs/2304.09590}, + doi = {10.48550/arXiv.2304.09590}, + abstract = {This paper describes the design and implementation of parallel neural networks (PNNs) with the novel programming language Golang. We follow in our approach the classical Single-Program Multiple-Data (SPMD) model where a PNN is composed of several sequential neural networks, which are trained with a proportional share of the training dataset. We used for this purpose the MNIST dataset, which contains binary images of handwritten digits. Our analysis focusses on different activation functions and optimizations in the form of stochastic gradients and initialization of weights and biases. We conduct a thorough performance analysis, where network configurations and different performance factors are analyzed and interpreted. Golang and its inherent parallelization support proved very well for parallel neural network simulation by considerable decreased processing times compared to sequential variants.}, + urldate = {2024-08-23}, publisher = {arXiv}, - author = {Zhang, Arthur Jun}, + author = {Kalwarowskyj, Daniela and Schikuta, Erich}, month = apr, year = {2023}, - note = {arXiv:2304.12833 [cs, math]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Information Retrieval, Computer Science - Information Theory}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/RREK5VQY/Zhang - 2023 - A New Information Theory of Certainty for Machine .pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/MS3Y5DB3/2304.html:text/html}, + note = {arXiv:2304.09590 [cs]}, + keywords = {68T07, Computer Science - Neural and Evolutionary Computing, I.2, Computer Science - Distributed, Parallel, and Cluster Computing}, + annote = {Comment: Extended version of paper Daniela Kalwarowskyj and Erich Schikuta, SPMD-based Neural Network Simulation with Golang, published at International Conference on Computational Science (ICCS) 2023}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/HBBHLAUI/Kalwarowskyj and Schikuta - 2023 - Parallel Neural Networks in Golang.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/V6W59QV2/2304.html:text/html}, +} + +@misc{petryk_importance_2024, + title = {On the {Importance} of {Reproducibility} of {Experimental} {Results} {Especially} in the {Domain} of {Security}}, + url = {http://arxiv.org/abs/2407.06760}, + doi = {10.1109/MECO62516.2024.10577919}, + abstract = {Security especially in the fields of IoT, industrial automation and critical infrastructure is paramount nowadays and a hot research topic. In order to ensure confidence in research results they need to be reproducible. In the past we reported [18] that in many publications important information such as details about the equipment used are missing. In this paper we report on our own experiments that we run to verify the parameters reported in the datasheets that came along with our experimental equipment. Our results show that there are significant discrepancies between the datasheets and the real world data. These deviations concern accuracy of positions, movements, duration of laser shots etc. In order to improve reproducibility of results we therefore argue on the one hand that research groups verify the data given in datasheets of equipment they use and on the other hand that they provide measurement set-up parameters in globally accepted units such as cm, seconds, etc.}, + urldate = {2024-07-10}, + author = {Petryk, Dmytro and Kabin, Ievgen and Langendörfer, Peter and Dyka, Zoya}, + month = jul, + year = {2024}, + note = {arXiv:2407.06760 [cs]}, + keywords = {Computer Science - Cryptography and Security, Computer Science - Hardware Architecture}, + annote = {Comment: 4 figures, 3 tables}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/HJHIXPCN/Petryk et al. - 2024 - On the Importance of Reproducibility of Experiment.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/6BBHTLMP/2407.html:text/html}, } @misc{qiao_we-math_2024, @@ -175,69 +282,178 @@ @misc{qiao_we-math_2024 year = {2024}, note = {arXiv:2407.01284 [cs]}, keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Symbolic Computation}, + annote = {Comment: Work in progress}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/IU5B49TG/Qiao et al. - 2024 - We-Math Does Your Large Multimodal Model Achieve .pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/NSFPNXAV/2407.html:text/html}, } -@misc{petryk_importance_2024, - title = {On the {Importance} of {Reproducibility} of {Experimental} {Results} {Especially} in the {Domain} of {Security}}, - url = {http://arxiv.org/abs/2407.06760}, - doi = {10.1109/MECO62516.2024.10577919}, - abstract = {Security especially in the fields of IoT, industrial automation and critical infrastructure is paramount nowadays and a hot research topic. In order to ensure confidence in research results they need to be reproducible. In the past we reported [18] that in many publications important information such as details about the equipment used are missing. In this paper we report on our own experiments that we run to verify the parameters reported in the datasheets that came along with our experimental equipment. Our results show that there are significant discrepancies between the datasheets and the real world data. These deviations concern accuracy of positions, movements, duration of laser shots etc. In order to improve reproducibility of results we therefore argue on the one hand that research groups verify the data given in datasheets of equipment they use and on the other hand that they provide measurement set-up parameters in globally accepted units such as cm, seconds, etc.}, - urldate = {2024-07-10}, - author = {Petryk, Dmytro and Kabin, Ievgen and Langendörfer, Peter and Dyka, Zoya}, - month = jul, - year = {2024}, - note = {arXiv:2407.06760 [cs]}, - keywords = {Computer Science - Cryptography and Security, Computer Science - Hardware Architecture}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/HJHIXPCN/Petryk et al. - 2024 - On the Importance of Reproducibility of Experiment.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/6BBHTLMP/2407.html:text/html}, +@misc{zhang_new_2023, + title = {A {New} {Information} {Theory} of {Certainty} for {Machine} {Learning}}, + url = {http://arxiv.org/abs/2304.12833}, + doi = {10.48550/arXiv.2304.12833}, + abstract = {Claude Shannon coined entropy to quantify the uncertainty of a random distribution for communication coding theory. We observe that the uncertainty nature of entropy also limits its direct usage in mathematical modeling. Therefore we propose a new concept troenpy,as the canonical dual of entropy, to quantify the certainty of the underlying distribution. We demonstrate two applications in machine learning. The first is for the classical document classification, we develop a troenpy based weighting scheme to leverage the document class label. The second is a self-troenpy weighting scheme for sequential data and show that it can be easily included in neural network based language models and achieve dramatic perplexity reduction. We also define quantum troenpy as the dual of the Von Neumann entropy to quantify the certainty of quantum systems.}, + urldate = {2024-07-07}, + publisher = {arXiv}, + author = {Zhang, Arthur Jun}, + month = apr, + year = {2023}, + note = {arXiv:2304.12833 [cs, math]}, + keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Information Retrieval, Computer Science - Information Theory}, + annote = {Comment: 24 pages, 3 figures, 1 table}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/RREK5VQY/Zhang - 2023 - A New Information Theory of Certainty for Machine .pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/MS3Y5DB3/2304.html:text/html}, +} + +@misc{vaswani_attention_2023, + title = {Attention {Is} {All} {You} {Need}}, + url = {http://arxiv.org/abs/1706.03762}, + doi = {10.48550/arXiv.1706.03762}, + abstract = {The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.}, + urldate = {2024-06-19}, + publisher = {arXiv}, + author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Lukasz and Polosukhin, Illia}, + month = aug, + year = {2023}, + note = {arXiv:1706.03762 [cs]}, + keywords = {Computer Science - Machine Learning, Computer Science - Computation and Language}, + annote = {Comment: 15 pages, 5 figures}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/335MFALG/Vaswani et al. - 2023 - Attention Is All You Need.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/KR7F69YM/1706.html:text/html}, +} + +@misc{yi_neural-symbolic_2019, + title = {Neural-{Symbolic} {VQA}: {Disentangling} {Reasoning} from {Vision} and {Language} {Understanding}}, + shorttitle = {Neural-{Symbolic} {VQA}}, + url = {http://arxiv.org/abs/1810.02338}, + doi = {10.48550/arXiv.1810.02338}, + abstract = {We marry two powerful ideas: deep representation learning for visual recognition and language understanding, and symbolic program execution for reasoning. Our neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question. It then executes the program on the scene representation to obtain an answer. Incorporating symbolic structure as prior knowledge offers three unique advantages. First, executing programs on a symbolic space is more robust to long program traces; our model can solve complex reasoning tasks better, achieving an accuracy of 99.8\% on the CLEVR dataset. Second, the model is more data- and memory-efficient: it performs well after learning on a small number of training data; it can also encode an image into a compact representation, requiring less storage than existing methods for offline question answering. Third, symbolic program execution offers full transparency to the reasoning process; we are thus able to interpret and diagnose each execution step.}, + urldate = {2024-06-17}, + publisher = {arXiv}, + author = {Yi, Kexin and Wu, Jiajun and Gan, Chuang and Torralba, Antonio and Kohli, Pushmeet and Tenenbaum, Joshua B.}, + month = jan, + year = {2019}, + note = {arXiv:1810.02338 [cs]}, + keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition}, + annote = {Comment: NeurIPS 2018 (spotlight). The first two authors contributed equally to this work. Project page: http://nsvqa.csail.mit.edu}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/WQ8SJ528/Yi et al. - 2019 - Neural-Symbolic VQA Disentangling Reasoning from .pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/9CIDLP4A/1810.html:text/html}, +} + +@misc{battaglia_relational_2018, + title = {Relational inductive biases, deep learning, and graph networks}, + url = {http://arxiv.org/abs/1806.01261}, + doi = {10.48550/arXiv.1806.01261}, + abstract = {Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between "hand-engineering" and "end-to-end" learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.}, + urldate = {2024-06-17}, + publisher = {arXiv}, + author = {Battaglia, Peter W. and Hamrick, Jessica B. and Bapst, Victor and Sanchez-Gonzalez, Alvaro and Zambaldi, Vinicius and Malinowski, Mateusz and Tacchetti, Andrea and Raposo, David and Santoro, Adam and Faulkner, Ryan and Gulcehre, Caglar and Song, Francis and Ballard, Andrew and Gilmer, Justin and Dahl, George and Vaswani, Ashish and Allen, Kelsey and Nash, Charles and Langston, Victoria and Dyer, Chris and Heess, Nicolas and Wierstra, Daan and Kohli, Pushmeet and Botvinick, Matt and Vinyals, Oriol and Li, Yujia and Pascanu, Razvan}, + month = oct, + year = {2018}, + note = {arXiv:1806.01261 [cs, stat]}, + keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Statistics - Machine Learning}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/S6TRQ9KR/Battaglia et al. - 2018 - Relational inductive biases, deep learning, and gr.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/JRHFDMQ4/1806.html:text/html}, +} + +@misc{lamb_graph_2021, + title = {Graph {Neural} {Networks} {Meet} {Neural}-{Symbolic} {Computing}: {A} {Survey} and {Perspective}}, + shorttitle = {Graph {Neural} {Networks} {Meet} {Neural}-{Symbolic} {Computing}}, + url = {http://arxiv.org/abs/2003.00330}, + doi = {10.48550/arXiv.2003.00330}, + abstract = {Neural-symbolic computing has now become the subject of interest of both academic and industry research laboratories. Graph Neural Networks (GNN) have been widely used in relational and symbolic domains, with widespread application of GNNs in combinatorial optimization, constraint satisfaction, relational reasoning and other scientific domains. The need for improved explainability, interpretability and trust of AI systems in general demands principled methodologies, as suggested by neural-symbolic computing. In this paper, we review the state-of-the-art on the use of GNNs as a model of neural-symbolic computing. This includes the application of GNNs in several domains as well as its relationship to current developments in neural-symbolic computing.}, + urldate = {2024-06-17}, + publisher = {arXiv}, + author = {Lamb, Luis C. and Garcez, Artur and Gori, Marco and Prates, Marcelo and Avelar, Pedro and Vardi, Moshe}, + month = jun, + year = {2021}, + note = {arXiv:2003.00330 [cs]}, + keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Logic in Computer Science}, + annote = {Comment: Updated version, draft of accepted IJCAI2020 Survey Paper}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/2SP4FU4E/Lamb et al. - 2021 - Graph Neural Networks Meet Neural-Symbolic Computi.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/URE2YKP9/2003.html:text/html}, +} + +@misc{noauthor_neuro-symbolic_nodate, + title = {Neuro-{Symbolic} {Artificial} {Intelligence} - workshops}, + url = {https://people.cs.ksu.edu/~hitzler/nesy/}, + urldate = {2024-06-17}, + file = {Neuro-Symbolic Artificial Intelligence:/home/rp152k/Zotero/storage/63DNPJFW/nesy.html:text/html}, +} + +@misc{de_raedt_statistical_2020, + title = {From {Statistical} {Relational} to {Neuro}-{Symbolic} {Artificial} {Intelligence}}, + url = {http://arxiv.org/abs/2003.08316}, + doi = {10.48550/arXiv.2003.08316}, + abstract = {Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these two fields. These cannot only be used to characterize and position neuro-symbolic artificial intelligence approaches but also to identify a number of directions for further research.}, + urldate = {2024-06-17}, + publisher = {arXiv}, + author = {De Raedt, Luc and Dumančić, Sebastijan and Manhaeve, Robin and Marra, Giuseppe}, + month = mar, + year = {2020}, + note = {arXiv:2003.08316 [cs]}, + keywords = {Computer Science - Artificial Intelligence}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/U4FGFF77/De Raedt et al. - 2020 - From Statistical Relational to Neuro-Symbolic Arti.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/8IVPLMHU/2003.html:text/html}, +} + +@misc{bottou_machine_2011, + title = {From {Machine} {Learning} to {Machine} {Reasoning}}, + url = {http://arxiv.org/abs/1102.1808}, + doi = {10.48550/arXiv.1102.1808}, + abstract = {A plausible definition of "reasoning" could be "algebraically manipulating previously acquired knowledge in order to answer a new question". This definition covers first-order logical inference or probabilistic inference. It also includes much simpler manipulations commonly used to build large learning systems. For instance, we can build an optical character recognition system by first training a character segmenter, an isolated character recognizer, and a language model, using appropriate labeled training sets. Adequately concatenating these modules and fine tuning the resulting system can be viewed as an algebraic operation in a space of models. The resulting model answers a new question, that is, converting the image of a text page into a computer readable text. This observation suggests a conceptual continuity between algebraically rich inference systems, such as logical or probabilistic inference, and simple manipulations, such as the mere concatenation of trainable learning systems. Therefore, instead of trying to bridge the gap between machine learning systems and sophisticated "all-purpose" inference mechanisms, we can instead algebraically enrich the set of manipulations applicable to training systems, and build reasoning capabilities from the ground up.}, + urldate = {2024-06-17}, + publisher = {arXiv}, + author = {Bottou, Leon}, + month = feb, + year = {2011}, + note = {arXiv:1102.1808 [cs]}, + keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning}, + annote = {Comment: 15 pages - fix broken pagination in v2}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/MJ6VVSW2/Bottou - 2011 - From Machine Learning to Machine Reasoning.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/GYZQ2VD2/1102.html:text/html}, +} + +@article{hitzler_neural-symbolic_2020, + title = {Neural-symbolic integration and the {Semantic} {Web}}, + volume = {11}, + issn = {22104968, 15700844}, + url = {https://www.medra.org/servlet/aliasResolver?alias=iospress&doi=10.3233/SW-190368}, + doi = {10.3233/SW-190368}, + language = {en}, + number = {1}, + urldate = {2024-06-17}, + journal = {Semantic Web}, + author = {Hitzler, Pascal and Bianchi, Federico and Ebrahimi, Monireh and Sarker, Md Kamruzzaman}, + editor = {Janowicz, Krzysztof}, + month = jan, + year = {2020}, + pages = {3--11}, + file = {Hitzler et al. - 2020 - Neural-symbolic integration and the Semantic Web.pdf:/home/rp152k/Zotero/storage/TXQTYC6N/Hitzler et al. - 2020 - Neural-symbolic integration and the Semantic Web.pdf:application/pdf}, } -@misc{kalwarowskyj_parallel_2023, - title = {Parallel {Neural} {Networks} in {Golang}}, - url = {http://arxiv.org/abs/2304.09590}, - doi = {10.48550/arXiv.2304.09590}, - abstract = {This paper describes the design and implementation of parallel neural networks (PNNs) with the novel programming language Golang. We follow in our approach the classical Single-Program Multiple-Data (SPMD) model where a PNN is composed of several sequential neural networks, which are trained with a proportional share of the training dataset. We used for this purpose the MNIST dataset, which contains binary images of handwritten digits. Our analysis focusses on different activation functions and optimizations in the form of stochastic gradients and initialization of weights and biases. We conduct a thorough performance analysis, where network configurations and different performance factors are analyzed and interpreted. Golang and its inherent parallelization support proved very well for parallel neural network simulation by considerable decreased processing times compared to sequential variants.}, - urldate = {2024-08-23}, +@misc{garcez_neurosymbolic_2020, + title = {Neurosymbolic {AI}: {The} 3rd {Wave}}, + shorttitle = {Neurosymbolic {AI}}, + url = {http://arxiv.org/abs/2012.05876}, + doi = {10.48550/arXiv.2012.05876}, + abstract = {Current advances in Artificial Intelligence (AI) and Machine Learning (ML) have achieved unprecedented impact across research communities and industry. Nevertheless, concerns about trust, safety, interpretability and accountability of AI were raised by influential thinkers. Many have identified the need for well-founded knowledge representation and reasoning to be integrated with deep learning and for sound explainability. Neural-symbolic computing has been an active area of research for many years seeking to bring together robust learning in neural networks with reasoning and explainability via symbolic representations for network models. In this paper, we relate recent and early research results in neurosymbolic AI with the objective of identifying the key ingredients of the next wave of AI systems. We focus on research that integrates in a principled way neural network-based learning with symbolic knowledge representation and logical reasoning. The insights provided by 20 years of neural-symbolic computing are shown to shed new light onto the increasingly prominent role of trust, safety, interpretability and accountability of AI. We also identify promising directions and challenges for the next decade of AI research from the perspective of neural-symbolic systems.}, + urldate = {2024-06-17}, publisher = {arXiv}, - author = {Kalwarowskyj, Daniela and Schikuta, Erich}, - month = apr, - year = {2023}, - note = {arXiv:2304.09590 [cs]}, - keywords = {68T07, Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Neural and Evolutionary Computing, I.2}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/HBBHLAUI/Kalwarowskyj and Schikuta - 2023 - Parallel Neural Networks in Golang.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/V6W59QV2/2304.html:text/html}, + author = {Garcez, Artur d'Avila and Lamb, Luis C.}, + month = dec, + year = {2020}, + note = {arXiv:2012.05876 [cs]}, + keywords = {Computer Science - Artificial Intelligence, Computer Science - Machine Learning, I.2.4, I.2.6}, + annote = {Comment: 37 pages}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/62RGF8PB/Garcez and Lamb - 2020 - Neurosymbolic AI The 3rd Wave.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/3QTEEPKH/2012.html:text/html}, } -@misc{ueno_migrating_2024, - title = {Migrating {Existing} {Container} {Workload} to {Kubernetes} -- {LLM} {Based} {Approach} and {Evaluation}}, - url = {http://arxiv.org/abs/2408.11428}, - doi = {10.48550/arXiv.2408.11428}, - abstract = {Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One approach employs large language models (LLMs) to assist developers in generating Kubernetes manifests; however it is currently impossible to determine whether the output satisfies given specifications and is comprehensible. In this study, we proposed a benchmarking method for evaluating the effectiveness of LLMs in synthesizing manifests, using the Compose specification -- a standard widely adopted by application developers -- as input. The proposed benchmarking method revealed that LLMs generally produce accurate results that compensate for simple specification gaps. However, we also observed that inline comments for readability were often omitted, and completion accuracy was low for atypical inputs with unclear intentions.}, - urldate = {2024-08-23}, +@misc{sheth_neurosymbolic_2023, + title = {Neurosymbolic {AI} -- {Why}, {What}, and {How}}, + url = {http://arxiv.org/abs/2305.00813}, + doi = {10.48550/arXiv.2305.00813}, + abstract = {Humans interact with the environment using a combination of perception - transforming sensory inputs from their environment into symbols, and cognition - mapping symbols to knowledge about the environment for supporting abstraction, reasoning by analogy, and long-term planning. Human perception-inspired machine perception, in the context of AI, refers to large-scale pattern recognition from raw data using neural networks trained using self-supervised learning objectives such as next-word prediction or object recognition. On the other hand, machine cognition encompasses more complex computations, such as using knowledge of the environment to guide reasoning, analogy, and long-term planning. Humans can also control and explain their cognitive functions. This seems to require the retention of symbolic mappings from perception outputs to knowledge about their environment. For example, humans can follow and explain the guidelines and safety constraints driving their decision-making in safety-critical applications such as healthcare, criminal justice, and autonomous driving. This article introduces the rapidly emerging paradigm of Neurosymbolic AI combines neural networks and knowledge-guided symbolic approaches to create more capable and flexible AI systems. These systems have immense potential to advance both algorithm-level (e.g., abstraction, analogy, reasoning) and application-level (e.g., explainable and safety-constrained decision-making) capabilities of AI systems.}, + urldate = {2024-06-17}, publisher = {arXiv}, - author = {Ueno, Masaru and Uchiumi, Tetsuya}, - month = aug, - year = {2024}, - note = {arXiv:2408.11428 [cs]}, - keywords = {Computer Science - Software Engineering}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/3M5HNIV6/Ueno and Uchiumi - 2024 - Migrating Existing Container Workload to Kubernete.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/ATBNY8SK/2408.html:text/html}, -} - -@article{gupta_columnar_2021, - title = {Columnar storage and list-based processing for graph database management systems}, - volume = {14}, - issn = {2150-8097}, - url = {https://dl.acm.org/doi/10.14778/3476249.3476297}, - doi = {10.14778/3476249.3476297}, - abstract = {We revisit column-oriented storage and query processing techniques in the context of contemporary graph database management systems (GDBMSs). Similar to column-oriented RDBMSs, GDBMSs support read-heavy analytical workloads that however have fundamentally different data access patterns than traditional analytical workloads. We first derive a set of desiderata for optimizing storage and query processors of GDBMS based on their access patterns. We then present the design of columnar storage, compression, and query processing techniques based on these desiderata. In addition to showing direct integration of existing techniques from columnar RDBMSs, we also propose novel ones that are optimized for GDBMSs. These include a novel list-based query processor, which avoids expensive data copies of traditional block-based processors under many-to-many joins, a new data structure we call singleindexed edge property pages and an accompanying edge ID scheme, and a new application of Jacobson’s bit vector index for compressing NULL values and empty lists. We integrated our techniques into the GraphflowDB in-memory GDBMS. Through extensive experiments, we demonstrate the scalability and query performance benefits of our techniques.}, - language = {en}, - number = {11}, - urldate = {2024-09-07}, - journal = {Proceedings of the VLDB Endowment}, - author = {Gupta, Pranjal and Mhedhbi, Amine and Salihoglu, Semih}, - month = jul, - year = {2021}, - pages = {2491--2504}, - file = {Gupta et al. - 2021 - Columnar storage and list-based processing for gra.pdf:/home/rp152k/Zotero/storage/EAE8LYB9/Gupta et al. - 2021 - Columnar storage and list-based processing for gra.pdf:application/pdf}, + author = {Sheth, Amit and Roy, Kaushik and Gaur, Manas}, + month = may, + year = {2023}, + note = {arXiv:2305.00813 [cs]}, + keywords = {Computer Science - Artificial Intelligence}, + annote = {Comment: To appear in IEEE Intelligent Systems}, + file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/XKHCL4IW/Sheth et al. - 2023 - Neurosymbolic AI -- Why, What, and How.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/JWNHUYEJ/2305.html:text/html}, } @misc{noauthor_rabbit_nodate, @@ -275,6 +491,7 @@ @article{viand_sok_2021 note = {arXiv: 2101.07078 version: 1}, keywords = {Computer Science - Cryptography and Security}, + annote = {Comment: 13 pages, to appear in IEEE Symposium on Security and Privacy 2021}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/N2LQML23/Viand et al. - 2021 - SoK Fully Homomorphic Encryption Compilers.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/TKVA2A2C/2101.html:text/html}, } @@ -290,6 +507,7 @@ @article{nguyen_leep_2020 year = {2020}, note = {arXiv: 2002.12462}, keywords = {Computer Science - Machine Learning, Statistics - Machine Learning, Computer Science - Computer Vision and Pattern Recognition}, + annote = {Comment: Published at the International Conference on Machine Learning (ICML) 2020}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/BVKGGYNR/Nguyen et al. - 2020 - LEEP A New Measure to Evaluate Transferability of.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/AK7NKYD8/2002.html:text/html}, } @@ -309,6 +527,7 @@ @article{dalskov_secure_2020 note = {arXiv: 1910.12435}, keywords = {Computer Science - Machine Learning, Computer Science - Cryptography and Security}, pages = {355--375}, + annote = {Comment: 22 pages}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/GJLYQGMX/Dalskov et al. - 2020 - Secure Evaluation of Quantized Neural Networks.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/827RD3SA/1910.html:text/html}, } @@ -374,6 +593,7 @@ @article{chen_big_2020 year = {2020}, note = {arXiv: 2006.10029}, keywords = {Computer Science - Machine Learning, Statistics - Machine Learning, Computer Science - Computer Vision and Pattern Recognition}, + annote = {Comment: NeurIPS'2020. Code and pretrained models at https://github.com/google-research/simclr}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/QMG8JMSQ/Chen et al. - 2020 - Big Self-Supervised Models are Strong Semi-Supervi.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/T5JJEDAS/2006.html:text/html}, } @@ -403,6 +623,7 @@ @article{park_contrastive_2020 year = {2020}, note = {arXiv: 2007.15651}, keywords = {Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition}, + annote = {Comment: ECCV 2020. Please visit https://taesungp.github.io/ContrastiveUnpairedTranslation/ for introduction videos and more. v3 contains typo fixes and citation update}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/DRPQKEW6/Park et al. - 2020 - Contrastive Learning for Unpaired Image-to-Image T.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/IJYK88WN/2007.html:text/html}, } @@ -417,6 +638,7 @@ @article{zhu_unpaired_2020 year = {2020}, note = {arXiv: 1703.10593}, keywords = {Computer Science - Computer Vision and Pattern Recognition}, + annote = {Comment: An extended version of our ICCV 2017 paper, v7 fixed the typos and updated the implementation details. Code and data: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/KSRXCALI/Zhu et al. - 2020 - Unpaired Image-to-Image Translation using Cycle-Co.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/ALARMCP8/1703.html:text/html;Full Text:/home/rp152k/Zotero/storage/RV4Q7ZFZ/Zhu et al. - 2020 - Unpaired Image-to-Image Translation using Cycle-Co.pdf:application/pdf}, } @@ -433,6 +655,7 @@ @article{lehtinen_noise2noise_2018 note = {arXiv: 1803.04189 version: 3}, keywords = {Computer Science - Machine Learning, Statistics - Machine Learning, Computer Science - Computer Vision and Pattern Recognition}, + annote = {Comment: Added link to official implementation and updated MRI results to match it}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/MGYCLR2N/Lehtinen et al. - 2018 - Noise2Noise Learning Image Restoration without Cl.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/WHBR4TGH/1803.html:text/html}, } @@ -448,6 +671,7 @@ @article{zhou_w2s_2020 year = {2020}, note = {arXiv: 2003.05961}, keywords = {Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing}, + annote = {Comment: ECCVW 2020. Project page: {\textbackslash}}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/462ERVYC/Zhou et al. - 2020 - W2S Microscopy Data with Joint Denoising and Supe.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/IDUJMPMT/2003.html:text/html}, } @@ -470,199 +694,6 @@ @article{zhang_poisson-gaussian_2019 year = {2019}, note = {arXiv: 1812.10366}, keywords = {Computer Science - Machine Learning, Statistics - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing}, + annote = {Comment: Camera-ready version for CVPR 2019. The Fluorescence Microscopy Denoising (FMD) dataset is available at https://drive.google.com/drive/folders/1aygMzSDdoq63IqSk-ly8cMq0\_owup8UM}, file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/Z8F3K8VP/Zhang et al. - 2019 - A Poisson-Gaussian Denoising Dataset with Real Flu.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/QV8H6RY4/1812.html:text/html}, } - -@misc{ueno_migrating_2024-1, - title = {Migrating {Existing} {Container} {Workload} to {Kubernetes} -- {LLM} {Based} {Approach} and {Evaluation}}, - url = {https://arxiv.org/abs/2408.11428v1}, - abstract = {Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One approach employs large language models (LLMs) to assist developers in generating Kubernetes manifests; however it is currently impossible to determine whether the output satisfies given specifications and is comprehensible. In this study, we proposed a benchmarking method for evaluating the effectiveness of LLMs in synthesizing manifests, using the Compose specification -- a standard widely adopted by application developers -- as input. The proposed benchmarking method revealed that LLMs generally produce accurate results that compensate for simple specification gaps. However, we also observed that inline comments for readability were often omitted, and completion accuracy was low for atypical inputs with unclear intentions.}, - language = {en}, - urldate = {2024-09-07}, - journal = {arXiv.org}, - author = {Ueno, Masaru and Uchiumi, Tetsuya}, - month = aug, - year = {2024}, - file = {Full Text PDF:/home/rp152k/Zotero/storage/WA5WC5UC/Ueno and Uchiumi - 2024 - Migrating Existing Container Workload to Kubernete.pdf:application/pdf}, -} - -@misc{de_palma_funless_2024, - title = {{FunLess}: {Functions}-as-a-{Service} for {Private} {Edge} {Cloud} {Systems}}, - shorttitle = {{FunLess}}, - url = {http://arxiv.org/abs/2405.21009}, - doi = {10.48550/arXiv.2405.21009}, - abstract = {We present FunLess, a Function-as-a-Service (FaaS) platform tailored for the private edge cloud system. FunLess responds to recent trends that advocate for extending the coverage of serverless computing to private edge cloud systems and enhancing latency, security, and privacy while improving resource usage. Unlike existing solutions that rely on containers for function invocation, FunLess leverages WebAssembly (Wasm) as its runtime environment. Wasm's lightweight, sandboxed runtime is crucial to have functions run on constrained devices at the edge. Moreover, the advantages of using Wasm in FunLess include a consistent development and deployment environment for users and function portability (write once, run everywhere) We validate FunLess under different deployment scenarios, characterised by the presence/absence of constrained-resource devices (Raspberry Pi 3B+) and the (in)accessibility of container orchestration technologies - Kubernetes. We compare FunLess with three production-ready, widely adopted open-source FaaS platforms - OpenFaaS, Fission, and Knative. Our benchmarks confirm that FunLess is a proper solution for FaaS private edge cloud systems since it achieves performance comparable to the considered FaaS alternatives while it is the only fully-deployable alternative on constrained-resource devices, thanks to its small memory footprint.}, - urldate = {2024-09-07}, - publisher = {arXiv}, - author = {De Palma, Giuseppe and Giallorenzo, Saverio and Mauro, Jacopo and Trentin, Matteo and Zavattaro, Gianluigi}, - month = may, - year = {2024}, - note = {arXiv:2405.21009 [cs]}, - keywords = {Computer Science - Distributed, Parallel, and Cluster Computing}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/5QG9ZBAW/De Palma et al. - 2024 - FunLess Functions-as-a-Service for Private Edge C.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/2LVP2YTR/2405.html:text/html}, -} - -@misc{thijsman_trusting_2024, - title = {Trusting the {Cloud}-{Native} {Edge}: {Remotely} {Attested} {Kubernetes} {Workers}}, - shorttitle = {Trusting the {Cloud}-{Native} {Edge}}, - url = {http://arxiv.org/abs/2405.10131}, - doi = {10.48550/arXiv.2405.10131}, - abstract = {A Kubernetes cluster typically consists of trusted nodes, running within the confines of a physically secure datacenter. With recent advances in edge orchestration, this is no longer the case. This poses a new challenge: how can we trust a device that an attacker has physical access to? This paper presents an architecture and open-source implementation that securely enrolls edge devices as trusted Kubernetes worker nodes. By providing boot attestation rooted in a hardware Trusted Platform Module, a strong base of trust is provided. A new custom controller directs a modified version of Keylime to cross the cloud-edge gap and securely deliver unique cluster credentials required to enroll an edge worker. The controller dynamically grants and revokes these credentials based on attestation events, preventing a possibly compromised node from accessing sensitive cluster resources. We provide both a qualitative and a quantitative evaluation of the architecture. The qualitative scenarios prove its ability to attest and enroll an edge device with role-based access control (RBAC) permissions that dynamically adjust to attestation events. The quantitative evaluation reflects an average of 10.28 seconds delay incurred on the startup time of the edge node due to attestation for a total average enrollment time of 20.91 seconds. The presented architecture thus provides a strong base of trust, securing a physically exposed edge device and paving the way for a robust and resilient edge computing ecosystem.}, - urldate = {2024-09-07}, - publisher = {arXiv}, - author = {Thijsman, Jordi and Sebrechts, Merlijn and De Turck, Filip and Volckaert, Bruno}, - month = may, - year = {2024}, - note = {arXiv:2405.10131 [cs]}, - keywords = {Computer Science - Cryptography and Security}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/FWNQPCGP/Thijsman et al. - 2024 - Trusting the Cloud-Native Edge Remotely Attested .pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/5PCRPWUA/2405.html:text/html}, -} - -@misc{cvetkovic_dirigent_2024, - title = {Dirigent: {Lightweight} {Serverless} {Orchestration}}, - shorttitle = {Dirigent}, - url = {https://arxiv.org/abs/2404.16393v1}, - abstract = {While Function as a Service (FaaS) platforms can initialize function sandboxes on worker nodes in 10-100s of milliseconds, the latency to schedule functions in real FaaS clusters can be orders of magnitude higher. We find that the current approach of building FaaS cluster managers on top of legacy orchestration systems like Kubernetes leads to high scheduling delay at high sandbox churn, which is typical in FaaS clusters. While generic cluster managers use hierarchical abstractions and multiple internal components to manage and reconcile state with frequent persistent updates, this becomes a bottleneck for FaaS, where cluster state frequently changes as sandboxes are created on the critical path of requests. Based on our root cause analysis of performance issues in existing FaaS cluster managers, we propose Dirigent, a clean-slate system architecture for FaaS orchestration with three key principles. First, Dirigent optimizes internal cluster manager abstractions to simplify state management. Second, it eliminates persistent state updates on the critical path of function invocations, leveraging the fact that FaaS abstracts sandboxes from users to relax exact state reconstruction guarantees. Finally, Dirigent runs monolithic control and data planes to minimize internal communication overheads and maximize throughput. We compare Dirigent to state-of-the-art FaaS platforms and show that Dirigent reduces 99th percentile per-function scheduling latency for a production workload by 2.79x compared to AWS Lambda and can spin up 2500 sandboxes per second at low latency, which is 1250x more than with Knative.}, - language = {en}, - urldate = {2024-09-07}, - journal = {arXiv.org}, - author = {Cvetković, Lazar and Costa, François and Djokic, Mihajlo and Friedman, Michal and Klimovic, Ana}, - month = apr, - year = {2024}, - file = {Full Text PDF:/home/rp152k/Zotero/storage/YXK2X5XS/Cvetković et al. - 2024 - Dirigent Lightweight Serverless Orchestration.pdf:application/pdf}, -} - -@misc{zhang_no_2024, - title = {No {Man} is an {Island}: {Towards} {Fully} {Automatic} {Programming} by {Code} {Search}, {Code} {Generation} and {Program} {Repair}}, - shorttitle = {No {Man} is an {Island}}, - url = {https://arxiv.org/abs/2409.03267v1}, - abstract = {Automatic programming attempts to minimize human intervention in the generation of executable code, and has been a long-standing challenge in the software engineering community. To advance automatic programming, researchers are focusing on three primary directions: (1) code search that reuses existing code snippets from external databases; (2) code generation that produces new code snippets from natural language; and (3) program repair that refines existing code snippets by fixing detected bugs. Despite significant advancements, the effectiveness of state-of-the-art techniques is still limited, such as the usability of searched code and the correctness of generated code. Motivated by the real-world programming process, where developers usually use various external tools to aid their coding processes, such as code search engines and code testing tools, in this work, we propose {\textbackslash}toolname\{\}, an automatic programming framework that leverages recent large language models (LLMs) to integrate the three research areas to address their inherent limitations. In particular, our framework first leverages different code search strategies to retrieve similar code snippets, which are then used to further guide the code generation process of LLMs. Our framework further validates the quality of generated code by compilers and test cases, and constructs repair prompts to query LLMs for generating correct patches. We conduct preliminary experiments to demonstrate the potential of our framework, {\textbackslash}eg helping CodeLlama solve 267 programming problems with an improvement of 62.53{\textbackslash}\%. As a generic framework, {\textbackslash}toolname\{\} can integrate various code search, generation, and repair tools, combining these three research areas together for the first time. More importantly, it demonstrates the potential of using traditional SE tools to enhance the usability of LLMs in automatic programming.}, - language = {en}, - urldate = {2024-09-08}, - journal = {arXiv.org}, - author = {Zhang, Quanjun and Fang, Chunrong and Shang, Ye and Zhang, Tongke and Yu, Shengcheng and Chen, Zhenyu}, - month = sep, - year = {2024}, - file = {Full Text PDF:/home/rp152k/Zotero/storage/Y746HTV6/Zhang et al. - 2024 - No Man is an Island Towards Fully Automatic Progr.pdf:application/pdf}, -} - -@misc{mersha_explainable_2024, - title = {Explainable {Artificial} {Intelligence}: {A} {Survey} of {Needs}, {Techniques}, {Applications}, and {Future} {Direction}}, - shorttitle = {Explainable {Artificial} {Intelligence}}, - url = {https://arxiv.org/abs/2409.00265v1}, - abstract = {Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these challenges by providing explanations for how these models make decisions and predictions, ensuring transparency, accountability, and fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, and the scope of XAI techniques. However, there remains a gap in the literature as there are no comprehensive reviews that delve into the detailed mathematical representations, design methodologies of XAI models, and other associated aspects. This paper provides a comprehensive literature review encompassing common terminologies and definitions, the need for XAI, beneficiaries of XAI, a taxonomy of XAI methods, and the application of XAI methods in different application areas. The survey is aimed at XAI researchers, XAI practitioners, AI model developers, and XAI beneficiaries who are interested in enhancing the trustworthiness, transparency, accountability, and fairness of their AI models.}, - language = {en}, - urldate = {2024-09-08}, - journal = {arXiv.org}, - author = {Mersha, Melkamu and Lam, Khang and Wood, Joseph and AlShami, Ali and Kalita, Jugal}, - month = aug, - year = {2024}, - doi = {10.1016/j.neucom.2024.128111}, - file = {Full Text PDF:/home/rp152k/Zotero/storage/XNX3MQB8/Mersha et al. - 2024 - Explainable Artificial Intelligence A Survey of N.pdf:application/pdf}, -} - -@misc{guo_deepseek-coder_2024, - title = {{DeepSeek}-{Coder}: {When} the {Large} {Language} {Model} {Meets} {Programming} -- {The} {Rise} of {Code} {Intelligence}}, - shorttitle = {{DeepSeek}-{Coder}}, - url = {https://arxiv.org/abs/2401.14196v2}, - abstract = {The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extensive research and development. To address this, we introduce the DeepSeek-Coder series, a range of open-source code models with sizes from 1.3B to 33B, trained from scratch on 2 trillion tokens. These models are pre-trained on a high-quality project-level code corpus and employ a fill-in-the-blank task with a 16K window to enhance code generation and infilling. Our extensive evaluations demonstrate that DeepSeek-Coder not only achieves state-of-the-art performance among open-source code models across multiple benchmarks but also surpasses existing closed-source models like Codex and GPT-3.5. Furthermore, DeepSeek-Coder models are under a permissive license that allows for both research and unrestricted commercial use.}, - language = {en}, - urldate = {2024-09-08}, - journal = {arXiv.org}, - author = {Guo, Daya and Zhu, Qihao and Yang, Dejian and Xie, Zhenda and Dong, Kai and Zhang, Wentao and Chen, Guanting and Bi, Xiao and Wu, Y. and Li, Y. K. and Luo, Fuli and Xiong, Yingfei and Liang, Wenfeng}, - month = jan, - year = {2024}, - file = {Full Text PDF:/home/rp152k/Zotero/storage/N729SIHI/Guo et al. - 2024 - DeepSeek-Coder When the Large Language Model Meet.pdf:application/pdf}, -} - -@misc{astekin_comparative_2024, - title = {A {Comparative} {Study} on {Large} {Language} {Models} for {Log} {Parsing}}, - url = {http://arxiv.org/abs/2409.02474}, - doi = {10.1145/3674805.3686684}, - abstract = {Background: Log messages provide valuable information about the status of software systems. This information is provided in an unstructured fashion and automated approaches are applied to extract relevant parameters. To ease this process, log parsing can be applied, which transforms log messages into structured log templates. Recent advances in language models have led to several studies that apply ChatGPT to the task of log parsing with promising results. However, the performance of other state-of-the-art large language models (LLMs) on the log parsing task remains unclear. Aims: In this study, we investigate the current capability of state-of-the-art LLMs to perform log parsing. Method: We select six recent LLMs, including both paid proprietary (GPT-3.5, Claude 2.1) and four free-to-use open models, and compare their performance on system logs obtained from a selection of mature open-source projects. We design two different prompting approaches and apply the LLMs on 1, 354 log templates across 16 different projects. We evaluate their effectiveness, in the number of correctly identified templates, and the syntactic similarity between the generated templates and the ground truth. Results: We found that free-to-use models are able to compete with paid models, with CodeLlama extracting 10\% more log templates correctly than GPT-3.5. Moreover, we provide qualitative insights into the usability of language models (e.g., how easy it is to use their responses). Conclusions: Our results reveal that some of the smaller, free-to-use LLMs can considerably assist log parsing compared to their paid proprietary competitors, especially code-specialized models.}, - urldate = {2024-09-09}, - author = {Astekin, Merve and Hort, Max and Moonen, Leon}, - month = sep, - year = {2024}, - note = {arXiv:2409.02474 [cs]}, - keywords = {Computer Science - Computation and Language, Computer Science - Software Engineering}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/2QVCQWHG/Astekin et al. - 2024 - A Comparative Study on Large Language Models for L.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/U4ZMLUQB/2409.html:text/html}, -} - -@misc{ramadan_role_2024, - title = {The {Role} of {Artificial} {Intelligence} and {Machine} {Learning} in {Software} {Testing}}, - url = {http://arxiv.org/abs/2409.02693}, - doi = {10.48550/arXiv.2409.02693}, - abstract = {Artificial Intelligence (AI) and Machine Learning (ML) have significantly impacted various industries, including software development. Software testing, a crucial part of the software development lifecycle (SDLC), ensures the quality and reliability of software products. Traditionally, software testing has been a labor-intensive process requiring significant manual effort. However, the advent of AI and ML has transformed this landscape by introducing automation and intelligent decision-making capabilities. AI and ML technologies enhance the efficiency and effectiveness of software testing by automating complex tasks such as test case generation, test execution, and result analysis. These technologies reduce the time required for testing and improve the accuracy of defect detection, ultimately leading to higher quality software. AI can predict potential areas of failure by analyzing historical data and identifying patterns, which allows for more targeted and efficient testing. This paper explores the role of AI and ML in software testing by reviewing existing literature, analyzing current tools and techniques, and presenting case studies that demonstrate the practical benefits of these technologies. The literature review provides a comprehensive overview of the advancements in AI and ML applications in software testing, highlighting key methodologies and findings from various studies. The analysis of current tools showcases the capabilities of popular AI-driven testing tools such as Eggplant AI, Test.ai, Selenium, Appvance, Applitools Eyes, Katalon Studio, and Tricentis Tosca, each offering unique features and advantages. Case studies included in this paper illustrate real-world applications of AI and ML in software testing, showing significant improvements in testing efficiency, accuracy, and overall software quality.}, - urldate = {2024-09-09}, - publisher = {arXiv}, - author = {Ramadan, Ahmed and Yasin, Husam and Pektas, Burhan}, - month = sep, - year = {2024}, - note = {arXiv:2409.02693 [cs]}, - keywords = {Computer Science - Artificial Intelligence, Computer Science - Software Engineering}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/FGVSTR8X/Ramadan et al. - 2024 - The Role of Artificial Intelligence and Machine Le.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/73QW5ILT/2409.html:text/html}, -} - -@inproceedings{foster_cloud_2008, - title = {Cloud {Computing} and {Grid} {Computing} 360-{Degree} {Compared}}, - url = {http://arxiv.org/abs/0901.0131}, - doi = {10.1109/GCE.2008.4738445}, - abstract = {Cloud Computing has become another buzzword after Web 2.0. However, there are dozens of different definitions for Cloud Computing and there seems to be no consensus on what a Cloud is. On the other hand, Cloud Computing is not a completely new concept; it has intricate connection to the relatively new but thirteen-year established Grid Computing paradigm, and other relevant technologies such as utility computing, cluster computing, and distributed systems in general. This paper strives to compare and contrast Cloud Computing with Grid Computing from various angles and give insights into the essential characteristics of both.}, - urldate = {2024-09-09}, - booktitle = {2008 {Grid} {Computing} {Environments} {Workshop}}, - author = {Foster, Ian and Zhao, Yong and Raicu, Ioan and Lu, Shiyong}, - month = nov, - year = {2008}, - note = {arXiv:0901.0131 [cs]}, - keywords = {A.1, C.2.4, Computer Science - Distributed, Parallel, and Cluster Computing}, - pages = {1--10}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/B6P69NAM/Foster et al. - 2008 - Cloud Computing and Grid Computing 360-Degree Comp.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/7256YKC9/0901.html:text/html}, -} - -@misc{varghese_cloud_2019, - title = {Cloud {Futurology}}, - url = {http://arxiv.org/abs/1902.03656}, - doi = {10.48550/arXiv.1902.03656}, - abstract = {The Cloud has become integral to most Internet-based applications and user gadgets. This article provides a brief history of the Cloud and presents a researcher's view of the prospects for innovating at the infrastructure, middleware, and application and delivery levels of the already crowded Cloud computing stack.}, - urldate = {2024-09-09}, - publisher = {arXiv}, - author = {Varghese, Blesson and Leitner, Philipp and Ray, Suprio and Chard, Kyle and Barker, Adam and Elkhatib, Yehia and Herry, Herry and Hong, Cheol-Ho and Singer, Jeremy and Tso, Fung Po and Yoneki, Eiko and Zhani, Mohamed-Faten}, - month = feb, - year = {2019}, - note = {arXiv:1902.03656 [cs]}, - keywords = {Computer Science - Distributed, Parallel, and Cluster Computing}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/3SFQ82BX/Varghese et al. - 2019 - Cloud Futurology.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/UGM8DRHY/1902.html:text/html}, -} - -@misc{jonas_cloud_2019, - title = {Cloud {Programming} {Simplified}: {A} {Berkeley} {View} on {Serverless} {Computing}}, - shorttitle = {Cloud {Programming} {Simplified}}, - url = {http://arxiv.org/abs/1902.03383}, - doi = {10.48550/arXiv.1902.03383}, - abstract = {Serverless cloud computing handles virtually all the system administration operations needed to make it easier for programmers to use the cloud. It provides an interface that greatly simplifies cloud programming, and represents an evolution that parallels the transition from assembly language to high-level programming languages. This paper gives a quick history of cloud computing, including an accounting of the predictions of the 2009 Berkeley View of Cloud Computing paper, explains the motivation for serverless computing, describes applications that stretch the current limits of serverless, and then lists obstacles and research opportunities required for serverless computing to fulfill its full potential. Just as the 2009 paper identified challenges for the cloud and predicted they would be addressed and that cloud use would accelerate, we predict these issues are solvable and that serverless computing will grow to dominate the future of cloud computing.}, - urldate = {2024-09-09}, - publisher = {arXiv}, - author = {Jonas, Eric and Schleier-Smith, Johann and Sreekanti, Vikram and Tsai, Chia-Che and Khandelwal, Anurag and Pu, Qifan and Shankar, Vaishaal and Carreira, Joao and Krauth, Karl and Yadwadkar, Neeraja and Gonzalez, Joseph E. and Popa, Raluca Ada and Stoica, Ion and Patterson, David A.}, - month = feb, - year = {2019}, - note = {arXiv:1902.03383 [cs]}, - keywords = {Computer Science - Operating Systems}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/5U42GVFM/Jonas et al. - 2019 - Cloud Programming Simplified A Berkeley View on S.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/4XBHYBH3/1902.html:text/html}, -} - -@misc{lertpongrujikorn_object_2024, - title = {Object as a {Service}: {Simplifying} {Cloud}-{Native} {Development} through {Serverless} {Object} {Abstraction}}, - shorttitle = {Object as a {Service}}, - url = {http://arxiv.org/abs/2408.04898}, - doi = {10.48550/arXiv.2408.04898}, - abstract = {The function-as-a-service (FaaS) paradigm is envisioned as the next generation of cloud computing systems that mitigate the burden for cloud-native application developers by abstracting them from cloud resource management. However, it does not deal with the application data aspects. As such, developers have to intervene and undergo the burden of managing the application data, often via separate cloud storage services. To further streamline cloud-native application development, in this work, we propose a new paradigm, known as Object as a Service (OaaS) that encapsulates application data and functions into the cloud object abstraction. OaaS relieves developers from resource and data management burden while offering built-in optimization features. Inspired by OOP, OaaS incorporates access modifiers and inheritance into the serverless paradigm that: (a) prevents developers from compromising the system via accidentally accessing underlying data; and (b) enables software reuse in cloud-native application development. Furthermore, OaaS natively supports dataflow semantics. It enables developers to define function workflows while transparently handling data navigation, synchronization, and parallelism issues. To establish the OaaS paradigm, we develop a platform named Oparaca that offers state abstraction for structured and unstructured data with consistency and fault-tolerant guarantees. We evaluated Oparaca under real-world settings against state-of-the-art platforms with respect to the imposed overhead, scalability, and ease of use. The results demonstrate that the object abstraction provided by OaaS can streamline flexible and scalable cloud-native application development with an insignificant overhead on the underlying serverless system.}, - urldate = {2024-09-09}, - publisher = {arXiv}, - author = {Lertpongrujikorn, Pawissanutt and Salehi, Mohsen Amini}, - month = aug, - year = {2024}, - note = {arXiv:2408.04898 [cs]}, - keywords = {Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Operating Systems, Computer Science - Software Engineering}, - file = {arXiv Fulltext PDF:/home/rp152k/Zotero/storage/PEPQE9BN/Lertpongrujikorn and Salehi - 2024 - Object as a Service Simplifying Cloud-Native Deve.pdf:application/pdf;arXiv.org Snapshot:/home/rp152k/Zotero/storage/3RWB5Q69/2408.html:text/html}, -}