Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey

TL;DR

This survey reviews graph rewiring techniques that modify topology to address over-squashing and over-smoothing in GNNs, enhancing information flow and model performance.

Contribution

It provides a comprehensive overview of state-of-the-art graph rewiring methods, including their theoretical basis, implementation details, and performance considerations.

Findings

Rewiring techniques can mitigate over-squashing and over-smoothing in GNNs.

Different rewiring strategies offer trade-offs between complexity and effectiveness.

Rewiring improves GNNs' ability to propagate information across long graph distances.

Abstract

Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and over-smoothing, where repeated propagation makes node representations indistinguishable. Both phenomena stem from the interaction between message passing and the input topology, ultimately degrading information flow and limiting the performance of GNNs. In this survey, we examine graph rewiring techniques, a class of methods designed to modify the graph topology to enhance information propagation in GNNs. We provide a comprehensive review of state-of-the-art rewiring approaches, delving into their theoretical underpinnings, practical implementations, and performance trade-offs.