Pith. sign in

REVIEW 1 cited by

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.01951 v2 pith:VIL2A6NL submitted 2023-07-04 cs.LG cs.AIcs.ITmath.ITmath.OCstat.ML

classification cs.LGcs.AIcs.ITmath.ITmath.OCstat.ML
keywords classificationcollapseevolutionfeatureneuralgnnsgraphgraphs
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Mini-Batch Class Composition Bias in Link Prediction

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    Link prediction GNNs learn trivial mini-batch dependent heuristics via batch normalization instead of consistent graph representations aligned with node classification features.

Pith tools