mlsanityData to 7 Oct 2026

Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization

arXiv 2306.08076 ↗First posted 13 Jun 2023cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) generalization deals with the prevalent learning scenario where test distribution shifts from training distribution. With rising application demands and inherent complexity, graph OOD problems call for specialized solutions. While data-centric methods exhibit performance enhancements on many generic machine learning tasks, there is a notable absence of data augmentation methods tailored for graph OOD generalization. In this work, we propose to achieve graph OOD generalization with the novel design of non-Euclidean-space linear extrapolation. The proposed augmentation strategy extrapolates both structure and feature spaces to generate OOD graph data. Our design tailors OOD samples for specific shifts without corrupting underlying causal mechanisms. Theoretical analysis and empirical results evidence the effectiveness of our method in solving target shifts, showing substantial and constant improvements across various graph OOD tasks.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 69 of its 95 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

69 of 95 references.

References · 69

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2019Invariant Risk Minimizationcited by 1,832
  10. 2016Variational Graph Auto-Encoderscited by 1,373
  11. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  12. 2020Graph Contrastive Learning with Augmentationscited by 1,203
38 more
  1. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  2. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  3. 2020In Search of Lost Domain Generalizationcited by 1,042
  4. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  5. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  6. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  7. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  8. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  9. 2013Domain Generalization via Invariant Feature Representationcited by 622
  10. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  11. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  12. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  13. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  14. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  15. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  16. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 331
  17. 2020The Risks of Invariant Risk Minimizationcited by 262
  18. 2018Graph networks as learnable physics engines for inference and controlcited by 242
  19. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  20. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  21. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  22. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  23. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  24. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  25. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  26. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  27. 2018Measuring abstract reasoning in neural networkscited by 165
  28. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  29. 2019What Can Neural Networks Reason About?cited by 155
  30. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  31. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  32. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  33. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  34. 2020From Local Structures to Size Generalization in Graph Neural Networkscited by 119
  35. 2019Neural Execution of Graph Algorithmscited by 118
  36. 2020Deep Visual Domain Adaptationcited by 91
  37. 2021Heterogeneous Risk Minimizationcited by 90
  38. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 3.

10 papers.

  1. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  2. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  3. 2024Equivariance via Minimal Frame Averaging for More Symmetries and Efficiencycited by 18
  4. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  5. 2024How Interpretable Are Interpretable Graph Neural Networks?cited by 13
  6. 2024Dissecting the Failure of Invariant Learning on Graphscited by 5
  7. 2025Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalizationcited by 3
  8. 2024Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 2
  9. 2025Out-of-Distribution Generalization on Graphs via Progressive Inferencecited by 2
  10. 2025Out-of-Distribution Graph Models Mergingcited by 0