Leave Graphs Alone: Addressing Over-Squashing without Rewiring
Published in LoG, 2022
Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called ‘over-squashing’ phenomenon. As a remedy, graph rewiring mechanisms have been proposed as preprocessing steps. Graph Echo State Networks (GESNs) are a reservoir computing model for graphs, where node embeddings are recursively computed by an untrained message-passing function. In this paper, we show that GESNs can achieve a significantly better accuracy on six heterophilic node classification tasks without altering the graph connectivity, thus suggesting a different route for addressing the over-squashing problem.
Recommended citation: D. Tortorella, A. Micheli (2022). "Leave Graphs Alone: Addressing Over-Squashing without Rewiring" (Extended Abstract). Presented at the First Learning on Graphs Conference (LoG 2022), Virtual Event, December 9–12, 2022.
Download Paper