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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Ghogho, Mounir
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911963830812672
author Ghogho, Mounir
author_facet Ghogho, Mounir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15284
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processing
Ghogho, Mounir
Machine Learning
Signal Processing
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.
title Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processing
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2407.15284