mlsanityData to 7 Oct 2026

Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs

arXiv 2402.11153 ↗First posted 17 Feb 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Distribution shifts on graphs -- the data distribution discrepancies between training and testing a graph machine learning model, are often ubiquitous and unavoidable in real-world scenarios. Such shifts may severely deteriorate the performance of the model, posing significant challenges for reliable graph machine learning. Consequently, there has been a surge in research on graph Out-Of-Distribution (OOD) adaptation methods that aim to mitigate the distribution shifts and adapt the knowledge from one distribution to another. In our survey, we provide an up-to-date and forward-looking review of graph OOD adaptation methods, covering two main problem scenarios including training-time as well as test-time graph OOD adaptation. We start by formally formulating the two problems and then discuss different types of distribution shifts on graphs. Based on our proposed taxonomy for graph OOD adaptation, we systematically categorize the existing methods according to their learning paradigm and investigate the techniques behind them. Finally, we point out promising research directions and the corresponding challenges. We also provide a continuously updated reading list at https://github.com/kaize0409/Awesome-Graph-OOD-Adaptation.git

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 61 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

42 of 61 references.

References · 42

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2019Simplifying Graph Convolutional Networkscited by 1,470
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  6. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  7. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  8. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  9. 2020From Local Structures to Size Generalization in Graph Neural Networkscited by 119
  10. 2020Graphon Neural Networks and the Transferability of Graph Neural Networkscited by 117
  11. 2019DIVA: Domain Invariant Variational Autoencoderscited by 114
  12. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
30 more
  1. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  2. 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
  3. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  4. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  5. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  6. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  7. 2023Graph Prompt Learning: A Comprehensive Survey and Beyondcited by 61
  8. 2023Structural Re-weighting Improves Graph Domain Adaptationcited by 45
  9. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  10. 2019DANE: Domain Adaptive Network Embeddingcited by 43
  11. 2022Non-IID Transfer Learning on Graphscited by 43
  12. 2022Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networkscited by 39
  13. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  14. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  15. 2023GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learningcited by 32
  16. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 29
  17. 2022Fair Node Representation Learning via Adaptive Data Augmentationcited by 27
  18. 2023Semi-supervised Domain Adaptation in Graph Transfer Learningcited by 27
  19. 2022A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applicationscited by 23
  20. 2022Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transportcited by 19
  21. 2022Test-Time Training for Graph Neural Networkscited by 17
  22. 2023GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labelscited by 17
  23. 2022GraphTTA: Test Time Adaptation on Graph Neural Networkscited by 14
  24. 2023Explaining and Adapting Graph Conditional Shiftcited by 14
  25. 2022FakeEdge: Alleviate Dataset Shift in Link Predictioncited by 12
  26. 2023GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networkscited by 12
  27. 2023Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Networkcited by 10
  28. 2023Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfercited by 10
  29. 2024Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labelscited by 7
  30. 2022Shift-Robust Node Classification via Graph Adversarial Clusteringcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 3.

6 papers.

  1. 2024Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learningcited by 17
  2. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  3. 2025Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problemcited by 5
  4. 2024A Benchmark on Directed Graph Representation Learning in Hardware Designscited by 1
  5. 2025Robust OOD Graph Learning via Mean Constraints and Noise Reductioncited by 0
  6. 2025From Noisy to Native: LLM-driven Graph Restoration for Test-Time Graph Domain Adaptationcited by 0