mlsanityData to 7 Oct 2026

Finding Diverse and Predictable Subgraphs for Graph Domain Generalization

arXiv 2206.09345 ↗First posted 19 Jun 2022cs.LG cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

This paper focuses on out-of-distribution generalization on graphs where performance drops due to the unseen distribution shift. Previous graph domain generalization works always resort to learning an invariant predictor among different source domains. However, they assume sufficient source domains are available during training, posing huge challenges for realistic applications. By contrast, we propose a new graph domain generalization framework, dubbed as DPS, by constructing multiple populations from the source domains. Specifically, DPS aims to discover multiple Diverse and Predictable Subgraphs with a set of generators, namely, subgraphs are different from each other but all the them share the same semantics with the input graph. These generated source domains are exploited to learn an textitequi-predictive graph neural network (GNN) across domains, which is expected to generalize well to unseen target domains. Generally, DPS is model-agnostic that can be incorporated with various GNN backbones. Extensive experiments on both node-level and graph-level benchmarks shows that the proposed DPS achieves impressive performance for various graph domain generalization tasks.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 58 of its 70 references that are in the map. First posted on arXiv 19 Jun 2022.

Builds on

58 of 70 references.

References · 58

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2019Invariant Risk Minimizationcited by 1,832
  8. 2019Simplifying Graph Convolutional Networkscited by 1,470
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  10. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  11. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  12. 2016Deep Variational Information Bottleneckcited by 915
38 more
  1. 2020Simple and Deep Graph Convolutional Networkscited by 857
  2. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  3. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  4. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  5. 2019Graph Neural Networks for Social Recommendationcited by 711
  6. 2018MINE: Mutual Information Neural Estimationcited by 680
  7. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  8. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  9. 2019Multi-scale Attributed Node Embeddingcited by 543
  10. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  11. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  12. 2019Graph U-Netscited by 489
  13. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  14. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  15. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  16. 2020Learning to Learn Single Domain Generalizationcited by 295
  17. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  18. 2017Concrete Dropoutcited by 227
  19. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  20. 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
  21. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  22. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  23. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  24. 2020Graph Information Bottleneckcited by 168
  25. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  26. 2020Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networkscited by 152
  27. 2017Invariant Causal Prediction for Nonlinear Modelscited by 140
  28. 2018Invariance, Causality and Robustnesscited by 123
  29. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  30. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  31. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  32. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  33. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  34. 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
  35. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  36. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  37. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  38. 2021Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalizationcited by 70

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 2; 2026: 1.

9 papers.

  1. 2023GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Expertscited by 19
  2. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  3. 2023Graph Structure and Feature Extrapolation for Out-of-Distribution Generalizationcited by 10
  4. 2024Subgraph Aggregation for Out-of-Distribution Generalization on Graphscited by 4
  5. 2024Subequivariant Reinforcement Learning Framework for Coordinated Motion Controlcited by 2
  6. 2025Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environmentscited by 2
  7. 2025Graph Augmentation for Cross Graph Domain Generalizationcited by 1
  8. 2023Is Self-Supervised Pretraining Good for Extrapolation in Molecular Property Prediction?cited by 0
  9. 2026Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimizationcited by 0