mlsanityData to 7 Oct 2026

Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities

arXiv 2204.07321 ↗First posted 15 Apr 2022cs.LGcited by 52

Not on the map. Why?

Abstract (arXiv)

Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation. As an essential component of the architecture, graph pooling is indispensable for obtaining a holistic graph-level representation of the whole graph. Although a great variety of methods have been proposed in this promising and fast-developing research field, to the best of our knowledge, little effort has been made to systematically summarize these works. To set the stage for the development of future works, in this paper, we attempt to fill this gap by providing a broad review of recent methods for graph pooling. Specifically, 1) we first propose a taxonomy of existing graph pooling methods with a mathematical summary for each category; 2) then, we provide an overview of the libraries related to graph pooling, including the commonly used datasets, model architectures for downstream tasks, and open-source implementations; 3) next, we further outline the applications that incorporate the idea of graph pooling in a variety of domains; 4) finally, we discuss certain critical challenges facing current studies and share our insights on future potential directions for research on the improvement of graph pooling.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 75 of its 111 references that are in the map. First posted on arXiv 15 Apr 2022.

Builds on

75 of 111 references.

References · 75

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2015Gated Graph Sequence Neural Networkscited by 792
  5. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  6. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  7. 2019Graph U-Netscited by 489
  8. 2019Self-Attention Graph Poolingcited by 421
  9. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  10. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  11. 2015Diffusion-Convolutional Neural Networkscited by 268
  12. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
38 more
  1. 2015Order Matters: Sequence to sequence for setscited by 236
  2. 2020Can Graph Neural Networks Count Substructures?cited by 235
  3. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  4. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  5. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  6. 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 160
  7. 2019ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representationscited by 156
  8. 2019Relational Pooling for Graph Representationscited by 150
  9. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  10. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 117
  11. 2018Towards Sparse Hierarchical Graph Classifierscited by 100
  12. 2019Graph Convolutional Networks with EigenPoolingcited by 94
  13. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  14. 2021Sequential Recommendation with Graph Neural Networkscited by 89
  15. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  16. 2019Hierarchical Graph Pooling with Structure Learningcited by 81
  17. 2020Rethinking pooling in graph neural networkscited by 73
  18. 2021Understanding Pooling in Graph Neural Networkscited by 69
  19. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 68
  20. 2021Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinitycited by 60
  21. 2019DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classificationcited by 59
  22. 2020Memory-Based Graph Networkscited by 56
  23. 2019Edge Contraction Pooling for Graph Neural Networkscited by 53
  24. 2020Topology-Aware Graph Pooling Networkscited by 44
  25. 2020Deep Learning for Community Detection: Progress, Challenges and Opportunitiescited by 42
  26. 2017Hybrid Approach of Relation Network and Localized Graph Convolutional Filtering for Breast Cancer Subtype Classificationcited by 40
  27. 2020Representation Learning of Histopathology Images using Graph Neural Networkscited by 40
  28. 2019Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classificationcited by 39
  29. 2021Edge Representation Learning with Hypergraphscited by 37
  30. 2021Pooling Architecture Search for Graph Classificationcited by 36
  31. 2020Path Integral Based Convolution and Pooling for Graph Neural Networkscited by 35
  32. 2020Second-Order Pooling for Graph Neural Networkscited by 33
  33. 2020Graph Cross Networks with Vertex Infomax Poolingcited by 31
  34. 2019Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Poolingcited by 30
  35. 2021EEG-GNN: Graph Neural Networks for Classification of Electroencephalogram (EEG) Signalscited by 28
  36. 2020Pooling Regularized Graph Neural Network for fMRI Biomarker Analysiscited by 25
  37. 2020Deep Graph Mapper: Seeing Graphs through the Neural Lenscited by 22
  38. 2019iPool -- Information-based Pooling in Hierarchical Graph Neural Networkscited by 21

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 10; 2024: 21; 2025: 10; 2026: 7.

52 papers.

Sort:

By area:

  1. 2023A graph convolutional autoencoder approach to model order reduction for parametrized PDEscited by 44
  2. 2023MAGIC: Detecting Advanced Persistent Threats via Masked Graph Representation Learningcited by 20
  3. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  4. 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
  5. 2024Graph Sparsification via Mixture of Graphscited by 17
  6. 2023Graph Neural Networks for Text Classification: A Surveycited by 15
  7. 2024GFN: A graph feedforward network for resolution-invariant reduced operator learning in multifidelity applicationscited by 10
  8. 2024A Survey on Graph Condensationcited by 9
  9. 2024Cluster-wise Graph Transformer with Dual-granularity Kernelized Attentioncited by 8
  10. 2024GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruningcited by 8
  11. 2023SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detectioncited by 7
  12. 2023PGODE: Towards High-quality System Dynamics Modelingcited by 7
38 more
  1. 2022QuadConv: Quadrature-Based Convolutions with Applications to Non-Uniform PDE Data Compressioncited by 6
  2. 2024Clustering for Protein Representation Learningcited by 6
  3. 2024A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizabilitycited by 6
  4. 2025Pool Me Wisely: On the Effect of Pooling in Transformer-Based Modelscited by 6
  5. 2024GEFL: Extended Filtration Learning for Graph Classificationcited by 5
  6. 2025Geometry-Aware Edge Pooling for Graph Neural Networkscited by 5
  7. 2024Graph Parsing Networkscited by 4
  8. 2025Towards Efficient Training of Graph Neural Networks: A Multiscale Approachcited by 4
  9. 2023Compressed Heterogeneous Graph for Abstractive Multi-Document Summarizationcited by 3
  10. 2023Domain independent post-processing with graph U-nets: Applications to Electrical Impedance Tomographic Imagingcited by 3
  11. 2024SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical featurescited by 3
  12. 2022Tackling Provably Hard Representative Selection via Graph Neural Networkscited by 2
  13. 2024Multi-object event graph representation learning for Video Question Answeringcited by 2
  14. 2024A Theory for Compressibility of Graph Transformers for Transductive Learningcited by 2
  15. 2023Careful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodescited by 1
  16. 2024Forward Learning of Graph Neural Networkscited by 1
  17. 2024Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic reviewcited by 1
  18. 2024Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approachcited by 1
  19. 2024Edge-Based Graph Component Poolingcited by 1
  20. 2026Hierarchical Discrete Flow Matching for Graph Generationcited by 1
  21. 2026TopoFormer: Topology Meets Attention for Graph Learningcited by 1
  22. 2022Hierarchical Graph Pooling is an Effective Citywide Traffic Condition Prediction Modelcited by 0
  23. 2023MSFormer: A Skeleton-multiview Fusion Method For Tooth Instance Segmentationcited by 0
  24. 2024A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systemscited by 0
  25. 20243DTextureTransformer: Geometry Aware Texture Generation for Arbitrary Mesh Topologycited by 0
  26. 2024Few-shot Learning on Heterogeneous Graphs: Challenges, Progress, and Prospectscited by 0
  27. 2024GSpect: Spectral Filtering for Cross-Scale Graph Classificationcited by 0
  28. 2024A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networkscited by 0
  29. 2025Learning Repetition-Invariant Representations for Polymer Informaticscited by 0
  30. 2025Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Poolingcited by 0
  31. 2025Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchiescited by 0
  32. 2025SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networkscited by 0
  33. 2025BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Predictioncited by 0
  34. 2025Enhancing Graph Classification Robustness with Singular Poolingcited by 0
  35. 2025BoolSkeleton: Boolean Network Skeletonization via Homogeneous Pattern Reductioncited by 0
  36. 2026Learning from Historical Activations in Graph Neural Networkscited by 0
  37. 2026GraphNNK -- Graph Classification and Interpretabilitycited by 0
  38. 2026GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learningcited by 0

50 most cited of 52 All 52 (JSON)