Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?

by   Haitao Mao, et al.

Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs. Notably, most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns, exhibiting a structural disparity. However, the analysis of GNN performance with respect to nodes exhibiting different structural patterns, e.g., homophilic nodes in heterophilic graphs, remains rather limited. In the present study, we provide evidence that Graph Neural Networks(GNNs) on node classification typically perform admirably on homophilic nodes within homophilic graphs and heterophilic nodes within heterophilic graphs while struggling on the opposite node set, exhibiting a performance disparity. We theoretically and empirically identify effects of GNNs on testing nodes exhibiting distinct structural patterns. We then propose a rigorous, non-i.i.d PAC-Bayesian generalization bound for GNNs, revealing reasons for the performance disparity, namely the aggregated feature distance and homophily ratio difference between training and testing nodes. Furthermore, we demonstrate the practical implications of our new findings via (1) elucidating the effectiveness of deeper GNNs; and (2) revealing an over-looked distribution shift factor on graph out-of-distribution problem and proposing a new scenario accordingly.


Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks

Graph neural networks (GNNs) have become compelling models designed to p...

Learning on Graphs with Out-of-Distribution Nodes

Graph Neural Networks (GNNs) are state-of-the-art models for performing ...

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Graph neural networks (GNNs) have become increasingly popular for classi...

On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks

Research on GNNs has highlighted a relationship between high homophily (...

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

Normalization plays an important role in the optimization of deep neural...

Disparity, Inequality, and Accuracy Tradeoffs in Graph Neural Networks for Node Classification

Graph neural networks (GNNs) are increasingly used in critical human app...

Size Generalizability of Graph Neural Networks on Biological Data: Insights and Practices from the Spectral Perspective

We investigate the question of whether the knowledge learned by graph ne...

Please sign up or login with your details

Forgot password? Click here to reset