2022/07/16 by Jakub Bober, Bober, Jakub, Anthea Monod +5 · 1 citation
Computer Science · Mathematics · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Topological and Geometric Data Analysis #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2207.08026
21 pages, 8 figures, 7 tables
arxiv created 2022/07/16 · openalex publication_date 2022/07/16 · arxiv updated 2022/07/19 · openalex created_date 2022/07/21 · openalex updated_date 2026/07/28
Information over-squashing is a phenomenon of inefficient information propagation between distant nodes on networks. It is an important problem that is known to significantly impact the training of graph neural networks (GNNs), as the receptive field of a node grows exponentially. To mitigate this problem, a preprocessing procedure known as rewiring is often applied to the input network. In this paper, we investigate the use of discrete analogues of classical geometric notions of curvature to model information flow on networks and rewire them. We show that these classical notions achieve state-of-the-art performance in GNN training accuracy on a variety of real-world network datasets. Moreover, compared to the current state-of-the-art, these classical notions exhibit a clear advantage in computational runtime by several orders of magnitude.