English

Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processing

Machine Learning 2024-07-23 v1 Signal Processing Machine Learning

Abstract

We delve into the issue of node classification within graphs, specifically reevaluating the concept of neighborhood aggregation, which is a fundamental component in graph neural networks (GNNs). Our analysis reveals conceptual flaws within certain benchmark GNN models when operating under the assumption of edge-independent node labels, a condition commonly observed in benchmark graphs employed for node classification. Approaching neighborhood aggregation from a statistical signal processing perspective, our investigation provides novel insights which may be used to design more efficient GNN models.

Keywords

Cite

@article{arxiv.2407.15284,
  title  = {Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processing},
  author = {Mounir Ghogho},
  journal= {arXiv preprint arXiv:2407.15284},
  year   = {2024}
}
R2 v1 2026-06-28T17:48:57.551Z