The Role of Node Features in Graph Pooling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |