Over-Squashing in Graph Neural Networks: A Comprehensive survey
It addresses a key bottleneck for researchers and practitioners in GNNs, but is incremental as a survey rather than a novel method.
This survey tackles the problem of over-squashing in Graph Neural Networks (GNNs), where long-range information dissemination is hindered, and comprehensively explores its causes, consequences, and mitigation strategies, including graph rewiring and curvature-based methods.
Graph Neural Networks (GNNs) revolutionize machine learning for graph-structured data, effectively capturing complex relationships. They disseminate information through interconnected nodes, but long-range interactions face challenges known as "over-squashing". This survey delves into the challenge of over-squashing in Graph Neural Networks (GNNs), where long-range information dissemination is hindered, impacting tasks reliant on intricate long-distance interactions. It comprehensively explores the causes, consequences, and mitigation strategies for over-squashing. Various methodologies are reviewed, including graph rewiring, novel normalization, spectral analysis, and curvature-based strategies, with a focus on their trade-offs and effectiveness. The survey also discusses the interplay between over-squashing and other GNN limitations, such as over-smoothing, and provides a taxonomy of models designed to address these issues in node and graph-level tasks. Benchmark datasets for performance evaluation are also detailed, making this survey a valuable resource for researchers and practitioners in the GNN field.