mlsanityData to 7 Oct 2026

Self-Attention Graph Pooling

arXiv 1904.08082 ↗First posted 17 Apr 2019cs.LG stat.MLcited by 421

Not on the map. Why?

Abstract (arXiv)

Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution and the downsampling (pooling) operations for graphs. The method of generalizing the convolution operation to graphs has been proven to improve performance and is widely used. However, the method of applying downsampling to graphs is still difficult to perform and has room for improvement. In this paper, we propose a graph pooling method based on self-attention. Self-attention using graph convolution allows our pooling method to consider both node features and graph topology. To ensure a fair comparison, the same training procedures and model architectures were used for the existing pooling methods and our method. The experimental results demonstrate that our method achieves superior graph classification performance on the benchmark datasets using a reasonable number of parameters.

Key facts. Cited by 421 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 92; 2022: 93; 2023: 79; 2024: 86; 2025: 44; 2026: 27.

421 papers.

Sort:

By area:

  1. 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 193
  2. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  3. 2022Graph neural networks for materials science and chemistrycited by 181
  4. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 173
  5. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
  6. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  7. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  8. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  9. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  10. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  11. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  12. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
38 more
  1. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  2. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  3. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  4. 2021Directed Acyclic Graph Neural Networkscited by 70
  5. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  6. 2021Understanding Pooling in Graph Neural Networkscited by 69
  7. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 69
  8. 2021Video as Conditional Graph Hierarchy for Multi-Granular Question Answeringcited by 68
  9. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  10. 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
  11. 2021Graph Coarsening with Neural Networkscited by 55
  12. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  13. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  14. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  15. 2021How Framelets Enhance Graph Neural Networkscited by 46
  16. 2023CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classificationcited by 46
  17. 2022Learning Pedestrian Group Representations for Multi-modal Trajectory Predictioncited by 44
  18. 2021A Survey on Graph-Based Deep Learning for Computational Histopathologycited by 41
  19. 2021JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answeringcited by 40
  20. 2023Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphscited by 39
  21. 2021Edge Representation Learning with Hypergraphscited by 37
  22. 2021Pooling Architecture Search for Graph Classificationcited by 36
  23. 2021Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Predictioncited by 36
  24. 2022Cross-modal Learning for Image-Guided Point Cloud Shape Completioncited by 36
  25. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  26. 2023The expressive power of pooling in Graph Neural Networkscited by 35
  27. 2022Cell Attention Networkscited by 34
  28. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  29. 2021Group-Aware Graph Neural Network for Nationwide City Air Quality Forecastingcited by 32
  30. 2024Graph Transformers: A Surveycited by 32
  31. 2022Evidence-aware Fake News Detection with Graph Neural Networkscited by 30
  32. 2021Visual Scene Graphs for Audio Source Separationcited by 29
  33. 2021Spatio-Temporal Scene-Graph Embedding for Autonomous Vehicle Collision Predictioncited by 29
  34. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  35. 2021EEG-GNN: Graph Neural Networks for Classification of Electroencephalogram (EEG) Signalscited by 28
  36. 2021A Hard Label Black-box Adversarial Attack Against Graph Neural Networkscited by 26
  37. 2022Stochastic Weight Averaging Revisitedcited by 26
  38. 2022Higher-order Clustering and Pooling for Graph Neural Networkscited by 26

50 most cited of 421 All 421 (JSON)