mlsanityData to 7 Oct 2026

Rethinking pooling in graph neural networks

arXiv 2010.11418 ↗First posted 22 Oct 2020cs.LG cs.AI cs.CVcited by 73

Not on the map. Why?

Abstract (arXiv)

Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Strikingly, our experiments demonstrate that using these variants does not result in any decrease in performance. To understand this phenomenon, we study the interplay between convolutional layers and the subsequent pooling ones. We show that the convolutions play a leading role in the learned representations. In contrast to the common belief, local pooling is not responsible for the success of GNNs on relevant and widely-used benchmarks.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 26; 2023: 11; 2024: 8; 2025: 10; 2026: 4.

73 papers.

Sort:

By area:

  1. 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 193
  2. 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
  3. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  4. 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
  5. 2022DiffWire: Inductive Graph Rewiring via the Lov'asz Boundcited by 79
  6. 2022BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networkscited by 73
  7. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  8. 2021Understanding Pooling in Graph Neural Networkscited by 69
  9. 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
  10. 2024Efficient Tuning and Inference for Large Language Models on Textual Graphscited by 54
  11. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  12. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
38 more
  1. 2022Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNcited by 43
  2. 2021On Representation Knowledge Distillation for Graph Neural Networkscited by 38
  3. 2021Pooling Architecture Search for Graph Classificationcited by 36
  4. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  5. 2023The expressive power of pooling in Graph Neural Networkscited by 35
  6. 2025KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systemscited by 35
  7. 2022Higher-order Clustering and Pooling for Graph Neural Networkscited by 26
  8. 2022A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applicationscited by 23
  9. 2022Rethinking Graph Convolutional Networks in Knowledge Graph Completioncited by 20
  10. 2022Template based Graph Neural Network with Optimal Transport Distancescited by 20
  11. 2021Graph Classification by Mixture of Diverse Expertscited by 16
  12. 2021Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learningcited by 14
  13. 2022Agent-based Graph Neural Networkscited by 13
  14. 2023Neural Bayes Estimators for Irregular Spatial Data using Graph Neural Networkscited by 13
  15. 2023A Survey of Graph Unlearningcited by 12
  16. 2025Exact Computation of Any-Order Shapley Interactions for Graph Neural Networkscited by 12
  17. 2022Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Successcited by 11
  18. 2022Image Classification using Graph Neural Network and Multiscale Wavelet Superpixelscited by 10
  19. 2024Boosting Graph Pooling with Persistent Homologycited by 9
  20. 2024Cluster-wise Graph Transformer with Dual-granularity Kernelized Attentioncited by 8
  21. 2022Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applicationscited by 7
  22. 2023Search to Capture Long-range Dependency with Stacking GNNs for Graph Classificationcited by 7
  23. 2021Diversified Multiscale Graph Learning with Graph Self-Correctioncited by 6
  24. 2021Structure-Aware Hierarchical Graph Pooling using Information Bottleneckcited by 6
  25. 2023State of the Art and Potentialities of Graph-level Learningcited by 6
  26. 2024A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizabilitycited by 6
  27. 2023Importance of equivariant and invariant symmetries for fluid flow modelingcited by 5
  28. 2025Geometry-Aware Edge Pooling for Graph Neural Networkscited by 5
  29. 2021Evaluating Modules in Graph Contrastive Learningcited by 4
  30. 2023Robust Ante-hoc Graph Explainer using Bilevel Optimizationcited by 4
  31. 2023On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Poolingcited by 4
  32. 2024Generalization Error of Graph Neural Networks in the Mean-field Regimecited by 4
  33. 2022Position-Aware Subgraph Neural Networks with Data-Efficient Learningcited by 3
  34. 2021Tree-Constrained Graph Neural Networks For Argument Miningcited by 2
  35. 2022DOTIN: Dropping Task-Irrelevant Nodes for GNNscited by 2
  36. 2022Embedding Graphs on Grassmann Manifoldcited by 2
  37. 2022On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processingcited by 2
  38. 2025Relieving the Over-Aggregating Effect in Graph Transformerscited by 2

50 most cited of 73 All 73 (JSON)