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

TL;DR

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

Contribution

It provides a comprehensive overview of state-of-the-art graph rewiring methods, analyzing their theoretical foundations, implementations, and trade-offs.

Findings

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

Different rewiring methods have varying impacts on GNN performance.

The survey highlights open challenges and future directions in graph rewiring for GNNs.

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.