mlsanityData to 7 Oct 2026

Hierarchical Graph Representation Learning with Differentiable Pooling

arXiv 1806.08804 ↗First posted 22 Jun 2018cs.LG cs.NE cs.SIcited by 786

Not on the map. Why?

Abstract (arXiv)

Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction. However, current GNN methods are inherently flat and do not learn hierarchical representations of graphs---a limitation that is especially problematic for the task of graph classification, where the goal is to predict the label associated with an entire graph. Here we propose DiffPool, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer. Our experimental results show that combining existing GNN methods with DiffPool yields an average improvement of 5-10% accuracy on graph classification benchmarks, compared to all existing pooling approaches, achieving a new state-of-the-art on four out of five benchmark data sets.

Key facts. Cited by 786 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 179; 2022: 173; 2023: 154; 2024: 124; 2025: 91; 2026: 64.

786 papers.

Sort:

By area:

  1. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  2. 2021Graph Self-Supervised Learning: A Surveycited by 289
  3. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  4. 2023Language is All a Graph Needscited by 219
  5. 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 193
  6. 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
  7. 2022Graph neural networks for materials science and chemistrycited by 181
  8. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  9. 2021The Values Encoded in Machine Learning Researchcited by 172
  10. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
  11. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  12. 2021Graph Condensation for Graph Neural Networkscited by 150
38 more
  1. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  2. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  3. 2021Nested Graph Neural Networkscited by 136
  4. 2022QuadTree Attention for Vision Transformerscited by 129
  5. 2023Dataset Distillation: A Comprehensive Reviewcited by 126
  6. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  7. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  8. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
  9. 2021Federated Graph Classification over Non-IID Graphscited by 113
  10. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 112
  11. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  12. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  13. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  14. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  15. 2022MultiScale MeshGraphNetscited by 94
  16. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  17. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  18. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  19. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  20. 2022Predicting Physics in Mesh-reduced Space with Temporal Attentioncited by 82
  21. 2021Graph Representation Learning in Biomedicinecited by 79
  22. 2022DiffWire: Inductive Graph Rewiring via the Lov'asz Boundcited by 79
  23. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  24. 2021User Preference-aware Fake News Detectioncited by 76
  25. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  26. 2022BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networkscited by 73
  27. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  28. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  29. 2021Understanding Pooling in Graph Neural Networkscited by 69
  30. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 69
  31. 2021Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Spacecited by 67
  32. 2021Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detectioncited by 67
  33. 2022A Survey on Graph Representation Learning Methodscited by 66
  34. 2021Reconstruction for Powerful Graph Representationscited by 65
  35. 2021Language-Agnostic Representation Learning of Source Code from Structure and Contextcited by 63
  36. 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
  37. 2024Human-inspired Episodic Memory for Infinite Context LLMscited by 62
  38. 2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58

50 most cited of 786 All 786 (JSON)