mlsanityData to 7 Oct 2026

Relational Pooling for Graph Representations

arXiv 1903.02541 ↗First posted 6 Mar 2019cs.LG stat.MLcited by 150

Not on the map. Why?

Abstract (arXiv)

This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and diffusions. Our approach, denoted Relational Pooling (RP), draws from the theory of finite partial exchangeability to provide a framework with maximal representation power for graphs. RP can work with existing graph representation models and, somewhat counterintuitively, can make them even more powerful than the original WL isomorphism test. Additionally, RP allows architectures like Recurrent Neural Networks and Convolutional Neural Networks to be used in a theoretically sound approach for graph classification. We demonstrate improved performance of RP-based graph representations over state-of-the-art methods on a number of tasks.

Key facts. Cited by 150 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 33; 2023: 34; 2024: 27; 2025: 21; 2026: 5.

150 papers.

Sort:

By area:

  1. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  2. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  3. 2021Combinatorial optimization and reasoning with graph neural networkscited by 267
  4. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  5. 2021Identity-aware Graph Neural Networkscited by 197
  6. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 166
  7. 2023Exphormer: Sparse Transformers for Graphscited by 166
  8. 2021Equivariant Subgraph Aggregation Networkscited by 154
  9. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
  10. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  11. 2021Nested Graph Neural Networkscited by 136
  12. 2021Scalars are universal: Equivariant machine learning, structured like classical physicscited by 127
38 more
  1. 2021Weisfeiler and Leman go Machine Learning: The Story so farcited by 121
  2. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
  3. 2021Global Self-Attention as a Replacement for Graph Convolutioncited by 113
  4. 2021Breaking the Limits of Message Passing Graph Neural Networkscited by 101
  5. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  6. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  7. 2022How Powerful are K-hop Message Passing Graph Neural Networkscited by 90
  8. 2024Graph Mamba: Towards Learning on Graphs with State Space Modelscited by 84
  9. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  10. 2023Attending to Graph Transformerscited by 81
  11. 2022A Survey on Graph Representation Learning Methodscited by 66
  12. 2021Reconstruction for Powerful Graph Representationscited by 65
  13. 2022Theory of Graph Neural Networks: Representation and Learningcited by 60
  14. 2022Ordered Subgraph Aggregation Networkscited by 57
  15. 2022Boosting the Cycle Counting Power of Graph Neural Networks with I2-GNNscited by 55
  16. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 55
  17. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  18. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 48
  19. 2022Message passing all the way upcited by 47
  20. 2021Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passingcited by 46
  21. 2022Shortest Path Networks for Graph Property Predictioncited by 46
  22. 2021Simple GNN Regularisation for 3D Molecular Property Prediction & Beyondcited by 44
  23. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  24. 2023Equivariant Polynomials for Graph Neural Networkscited by 38
  25. 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
  26. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  27. 2022SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networkscited by 36
  28. 2023An Empirical Study of Realized GNN Expressivenesscited by 33
  29. 2023Path Neural Networks: Expressive and Accurate Graph Neural Networkscited by 32
  30. 2023Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformerscited by 32
  31. 2023Graph Positional and Structural Encodercited by 31
  32. 2023WL meet VCcited by 30
  33. 2023The Expressive Power of Graph Neural Networks: A Surveycited by 27
  34. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  35. 2023Learning Probabilistic Symmetrization for Architecture Agnostic Equivariancecited by 25
  36. 2024A Canonicalization Perspective on Invariant and Equivariant Learningcited by 25
  37. 2022Molecular Representation Learning via Heterogeneous Motif Graph Neural Networkscited by 23
  38. 2023Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Typescited by 21

50 most cited of 150 All 150 (JSON)