The Role of Node Features in Graph Pooling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: von Pichowski, Jan, Hrabošová, Alžbeta, Scholtes, Ingo, Blöcker, Christopher
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910198304604160
author von Pichowski, Jan
Hrabošová, Alžbeta
Scholtes, Ingo
Blöcker, Christopher
author_facet von Pichowski, Jan
Hrabošová, Alžbeta
Scholtes, Ingo
Blöcker, Christopher
contents Graph pooling is commonly applied in graph classification, yet its empirical gains over standard WL-1 expressive GNNs are often marginal or inconsistent. We study this gap by analysing the interaction between node features and graph topology and their effect on pooling objectives. Our analysis reveals that pooling operators require node features that are well-aligned with the graph's topology -- a condition often overlooked and not guaranteed in empirical networks. We formalise fundamental requirements for node features to enable effective pooling, and introduce a quantitative measure of feature quality. Our empirical evaluation shows that, when these requirements are satisfied, pooling can be beneficial and improve performance on appropriate datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06250
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Role of Node Features in Graph Pooling
von Pichowski, Jan
Hrabošová, Alžbeta
Scholtes, Ingo
Blöcker, Christopher
Machine Learning
Graph pooling is commonly applied in graph classification, yet its empirical gains over standard WL-1 expressive GNNs are often marginal or inconsistent. We study this gap by analysing the interaction between node features and graph topology and their effect on pooling objectives. Our analysis reveals that pooling operators require node features that are well-aligned with the graph's topology -- a condition often overlooked and not guaranteed in empirical networks. We formalise fundamental requirements for node features to enable effective pooling, and introduce a quantitative measure of feature quality. Our empirical evaluation shows that, when these requirements are satisfied, pooling can be beneficial and improve performance on appropriate datasets.
title The Role of Node Features in Graph Pooling
topic Machine Learning
url https://arxiv.org/abs/2605.06250