2024-01-23-campbell24a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
DBGSL: Dynamic Brain Graph Structure Learning	Recently, graph neural networks (GNNs) have shown success at learning representations of brain graphs derived from functional magnetic resonance imaging (fMRI) data. The majority of existing GNN methods, however, assume brain graphs are static over time and the graph adjacency matrix is known prior to model training. These assumptions are at odds with neuroscientific evidence that brain graphs are time-varying with a connectivity structure that depends on the choice of functional connectivity measure. Noisy brain graphs that do not truly represent the underling fMRI data can have a detrimental impact on the performance of GNNs. As a solution, we propose Dynamic Brain Graph Structure Learning (DBGSL), a novel method for learning the optimal time-varying dependency structure of fMRI data induced by a downstream prediction task. Experiments demonstrate DBGSL achieves state-of-the-art performance for sex classification using real-world resting-state and task fMRI data. Moreover, analysis of the learnt dynamic graphs highlights prediction-related brain regions which align with existing neuroscience literature.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	campbell24a	0	DBGSL: Dynamic Brain Graph Structure Learning	1318	1345	1318-1345	1318	false	Campbell, Alexander and Zippo, Antonio Giuliano and Passamonti, Luca and Toschi, Nicola and Lio, Pietro	given family Alexander Campbell given family Antonio Giuliano Zippo given family Luca Passamonti given family Nicola Toschi given family Pietro Lio	2024-01-23		Medical Imaging with Deep Learning	227	inproceedings	date-parts 2024 1 23	https://proceedings.mlr.press/v227/campbell24a/campbell24a.pdf