mlsanityData to 7 Oct 2026

Out-Of-Distribution Generalization on Graphs: A Survey

arXiv 2202.07987 ↗First posted 16 Feb 2022cs.LGcited by 97

Not on the map. Why?

Abstract (arXiv)

Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where the model performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this critical problem, out-of-distribution (OOD) generalization on graphs, which goes beyond the in-distribution hypothesis, has made great progress and attracted ever-increasing attention from the research community. In this paper, we comprehensively survey OOD generalization on graphs and present a detailed review of recent advances in this area. First, we provide a formal problem definition of OOD generalization on graphs. Second, we categorize existing methods into three classes from conceptually different perspectives, i.e., data, model, and learning strategy, based on their positions in the graph machine learning pipeline, followed by detailed discussions for each category. We also review the theories related to OOD generalization on graphs and introduce the commonly used graph datasets for thorough evaluations. Finally, we share our insights on future research directions. This paper is the first systematic and comprehensive review of OOD generalization on graphs, to the best of our knowledge.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). Builds on 98 of its 190 references that are in the map. First posted on arXiv 16 Feb 2022.

Builds on

98 of 190 references.

References · 98

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  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. 2016Variational Graph Auto-Encoderscited by 1,373
  10. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  12. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
38 more
  1. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  2. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  3. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  4. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  5. 2021Domain Generalization: A Surveycited by 760
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  7. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  8. 2019Adversarial Training for Free!cited by 638
  9. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  10. 2019Multi-scale Attributed Node Embeddingcited by 543
  11. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  12. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 461
  13. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  14. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  15. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  16. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  17. 2020Learning Lane Graph Representations for Motion Forecastingcited by 380
  18. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  19. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  20. 2018Understanding disentangling in β-VAEcited by 332
  21. 2021Graph Self-Supervised Learning: A Surveycited by 289
  22. 2020Domain Generalization using Causal Matchingcited by 224
  23. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  24. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 218
  25. 2020Generalization and Representational Limits of Graph Neural Networkscited by 217
  26. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  27. 2020Data Augmentation for Graph Neural Networkscited by 200
  28. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  29. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  30. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  31. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  32. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  33. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  34. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  35. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 160
  36. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  37. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  38. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144

50 most cited of 98 All 98 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 20; 2024: 29; 2025: 19; 2026: 19.

97 papers.

Sort:

By area:

  1. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 271
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  3. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  4. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  5. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  6. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  7. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  8. 2023Towards Understanding the Generalization of Graph Neural Networkscited by 41
  9. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  10. 2023Mind the Label Shift of Augmentation-based Graph OOD Generalizationcited by 34
  11. 2022Graph Lifelong Learning: A Surveycited by 30
  12. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
38 more
  1. 2022WOODS: Benchmarks for Out-of-Distribution Generalization in Time Seriescited by 29
  2. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  3. 2023Federated Domain Generalization: A Surveycited by 25
  4. 2023Graph Meets LLMs: Towards Large Graph Modelscited by 19
  5. 2023GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Expertscited by 19
  6. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 18
  7. 2023GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labelscited by 17
  8. 2024Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learningcited by 17
  9. 2025Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesicscited by 17
  10. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  11. 2023Curriculum Graph Machine Learning: A Surveycited by 15
  12. 2023Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalizationcited by 15
  13. 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
  14. 2025Out-of-Distribution Generalization in Time Series: A Surveycited by 15
  15. 2022Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspectivecited by 13
  16. 2023Causality and Independence Enhancement for Biased Node Classificationcited by 13
  17. 2024Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspectivecited by 13
  18. 2024Online GNN Evaluation Under Test-time Graph Distribution Shiftscited by 12
  19. 2023Uncertainty Estimation for Molecules: Desiderata and Methodscited by 11
  20. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  21. 2023Identifying Semantic Component for Robust Molecular Property Predictioncited by 10
  22. 2024Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptationcited by 10
  23. 2022Finding Diverse and Predictable Subgraphs for Graph Domain Generalizationcited by 9
  24. 2023Combating Bilateral Edge Noise for Robust Link Predictioncited by 9
  25. 2026USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptationcited by 9
  26. 2023MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learningcited by 7
  27. 2024Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labelscited by 7
  28. 2024Cooperative Classification and Rationalization for Graph Generalizationcited by 7
  29. 2024Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenariocited by 7
  30. 2025Toward Robust Non-Transferable Learning: A Survey and Benchmarkcited by 7
  31. 2024Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphscited by 6
  32. 2024The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regretcited by 6
  33. 2024Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalizationcited by 6
  34. 2023Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Predictioncited by 5
  35. 2025Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problemcited by 5
  36. 2022Privacy and Transparency in Graph Machine Learning: A Unified Perspectivecited by 4
  37. 2023When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlookcited by 4
  38. 2024Causal Inference with Latent Variables: Recent Advances and Future Prospectivescited by 4

50 most cited of 97 All 97 (JSON)