2024-04-18-baker24a.md

title	software	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
Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs	https://github.com/Utah-Math-Data-Science/PR-inspired-aggregation	Learning long-range interactions (LRI) between distant nodes is crucial for many graph learning tasks. Predominant graph neural networks (GNNs) rely on local message passing and struggle to learn LRI. In this paper, we propose DRGNN to learn LRI leveraging monotone operator theory. DRGNN contains two key components: (1) we use a full node similarity matrix beyond adjacency matrix – drawing inspiration from the personalized PageRank matrix – as the aggregation matrix for message passing, and (2) we implement message-passing on graphs using Douglas-Rachford splitting to circumvent prohibitive matrix inversion. We demonstrate that DRGNN surpasses various advanced GNNs, including Transformer-based models, on several benchmark LRI learning tasks arising from different application domains, highlighting its efficacy in learning LRI. Code is available at \url{https://github.com/Utah-Math-Data-Science/PR-inspired-aggregation}.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	baker24a	0	Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs	2233	2241	2233-2241	2233	false	Baker, Justin M. and Wang, Qingsong and Berzins, Martin and Strohmer, Thomas and Wang, Bao	given family Justin M. Baker given family Qingsong Wang given family Martin Berzins given family Thomas Strohmer given family Bao Wang	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/baker24a/baker24a.pdf