English

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Machine Learning 2023-10-27 v2 Artificial Intelligence Information Theory math.IT Optimization and Control Machine Learning

Abstract

Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in GNNs is not well understood. In this paper, we focus on node-wise classification, illustrated with community detection on stochastic block model graphs, and explore the feature evolution through the lens of the "Neural Collapse" (NC) phenomenon. When training instance-wise deep classifiers (e.g. for image classification) beyond the zero training error point, NC demonstrates a reduction in the deepest features' within-class variability and an increased alignment of their class means to certain symmetric structures. We start with an empirical study that shows that a decrease in within-class variability is also prevalent in the node-wise classification setting, however, not to the extent observed in the instance-wise case. Then, we theoretically study this distinction. Specifically, we show that even an "optimistic" mathematical model requires that the graphs obey a strict structural condition in order to possess a minimizer with exact collapse. Interestingly, this condition is viable also for heterophilic graphs and relates to recent empirical studies on settings with improved GNNs' generalization. Furthermore, by studying the gradient dynamics of the theoretical model, we provide reasoning for the partial collapse observed empirically. Finally, we present a study on the evolution of within- and between-class feature variability across layers of a well-trained GNN and contrast the behavior with spectral methods.

Keywords

Cite

@article{arxiv.2307.01951,
  title  = {A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks},
  author = {Vignesh Kothapalli and Tom Tirer and Joan Bruna},
  journal= {arXiv preprint arXiv:2307.01951},
  year   = {2023}
}

Comments

NeurIPS 2023

R2 v1 2026-06-28T11:22:14.515Z