Graph representation learning (GRL) has been intensively studied and widely applied into various applications recently, such as social network, knowledge graph, recommender system, etc. One underlying assumption commonly adopted by these methods is that all attributes of nodes are complete. However, in practice, this assumption may not hold due to 1) the absence of particular attributes; 2) the absence of all the attributes of specific nodes. Here we provide collections for incomplete graph representation learning literature.

1. [IEEE TPAMI 2022] Learning on Attribute-Missing Graphs [paper|code]
2. [WWW 2022] Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data [paper|code]
3. [PR 2022] Incomplete Multiview Nonnegative Representation Learning with Multiple Graphs [paper]
4. [Arxiv 2022] MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs [paper]

1. [WWW 2021] Heterogeneous Graph Neural Network via Attribute Completion [paper|code]
2. [NeurIPS 2021] Subgraph Federated Learning with Missing Neighbor Generation [paper|code]
3. [NeurIPS 2021] Multi-view Contrastive Graph Clustering [paper|code]
4. [FGCS 2021] Graph Convolutional Networks for Graphs Containing Missing Features [paper|code]
5. [AAAI Workshop 2021] Context-Enhanced Entity and Relation Embedding for Knowledge Graph Completion [paper|code]
6. [KDD Workshop 2021] On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs [paper|code]
7. [CIKM 2021] Inductive Matrix Completion Using Graph Autoencoder [paper|code]
8. [Arxiv 2021] On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features [paper|code]
9. [Arxiv 2021] Incomplete Graph Representation and Learning via Partial Graph Neural Networks [paper|code]
10. [Arxiv 2021] Siamese Attribute-missing Graph Auto-encoder [paper|code]
11. [Arxiv 2021] Wasserstein diffusion on graphs with missing attributes [paper|code]
12. [Arxiv 2021] Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods [paper|code]
13. [Arxiv 2021] Link-Intensive Alignment for Incomplete Knowledge Graphs [paper|code]
14. [Arxiv 2021] Incomplete Multi-view Clustering via Cross-view Relation Transfer [paper|code]
15. [Arxiv 2021] VICAUSE: Simultaneous Missing Value Imputation and Causal Discovery with Groups [paper|code]
16. [Arxiv 2021] CORGI: Content-Rich Graph Neural Networks with Attention [paper|code]
17. [Arxiv 2021] Two-view Graph Neural Networks for Knowledge Graph Completion [paper|code]
18. [Arxiv 2021] SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs [paper|code]

1. [NeurIPS 2020] Handling Missing Data with Graph Representation Learning [paper|code]
2. [NeurIPS 2020] Matrix Completion with Hierarchical Graph Side Information [paper|code]
3. [NN 2020] Missing Data Imputation with Adversarially-trained Graph Convolutional Networks [paper|code]
4. [ICLR 2020] Inductive Matrix Completion Based on Graph Neural Networks [paper|code]
5. [EMNLP 2020] TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion [paper|code]
6. [EMNLP 2020] Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer [paper|code]
7. [EMNLP 2020] MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning [paper|code]
8. [Arxiv 2020] Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation [paper|code]

1. [KBS 2019] Adversarial Learning for Multi-view Network Embedding on Incomplete Graphs [paper|code]
2. [ICDM 2019] Learning to Hash for Efficient Search over Incomplete Knowledge Graphs [paper|code]
3. [Arxiv 2019] Node Attribute Generation on Graphs [paper|code]

1. [KDD 2018] Graph Convolutional Neural Networks for Web-Scale Recommender Systems [paper|code]
2. [ECCV Workshop 2018] Incomplete Multi-view Clustering via Graph Regularized Matrix Factorization [paper|code]
3. [RecSys 2018] Spectral collaborative filtering [paper|code]

1. [NeurIPS 2017] Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks [paper|code]
2. [Arxiv 2017] Graph Convolutional Matrix Completion [paper|code]

• awesome-deep-graph-clustering
• awesome-graph-representation-learning
• awesome-graph-self-supervised-learning
• awesome-self-supervised-gnn
• awesome-self-supervised-learning-for-graphs

If interested, you are welcome to contribute this repo by contracting [email protected].