mlsanityData to 14 Oct 2026

The Role of Node Features in Graph Pooling

arXiv 2605.06250 ↗First posted 7 May 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

26 of 35 references.

References · 26

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  5. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  6. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  7. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  8. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  9. 2020Benchmarking Graph Neural Networkscited by 680
  10. 2019Graph U-Netscited by 492
  11. 2019Self-Attention Graph Poolingcited by 421
  12. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
14 more
  1. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  2. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  3. 2020Graph Clustering with Graph Neural Networkscited by 163
  4. 20213D Infomax improves GNNs for Molecular Property Predictioncited by 146
  5. 2021Understanding Pooling in Graph Neural Networkscited by 69
  6. 2019Edge Contraction Pooling for Graph Neural Networkscited by 53
  7. 2019Overlapping Community Detection with Graph Neural Networkscited by 45
  8. 2023The expressive power of pooling in Graph Neural Networkscited by 35
  9. 2023Graph Positional and Structural Encodercited by 33
  10. 2019Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Poolingcited by 30
  11. 2024Expressivity and Generalization: Fragment-Biases for Molecular GNNscited by 9
  12. 2022Simplifying Clustering with Graph Neural Networkscited by 8
  13. 2022Generalizing Downsampling from Regular Data to Graphscited by 6
  14. 2024MDL-Pool: Adaptive Multilevel Graph Pooling Based on Minimum Description Lengthcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Unifying Graph Neural Networks Through a Common Layer Equationcited by 0