Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs (2402.11153v1)

Published 17 Feb 2024 in cs.LG

Abstract: 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

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Analysis of representations for domain adaptation. NeurIPS, 2006.
  2. Bridged-gnn: Knowledge bridge learning for effective knowledge transfer. In CIKM, 2023.
  3. Predicting the silent majority on graphs: Knowledge transferable graph neural network. In TheWebConf, 2023.
  4. Graph domain adaptation: A generative view. TKDD, 2024.
  5. Graphtta: Test time adaptation on graph neural networks. ICML, 2022.
  6. Learning causally invariant representations for out-of-distribution generalization on graphs. NeurIPS, 2022.
  7. Universal domain adaptive network embedding for node classification. In MM, 2023.
  8. Tree mover’s distance: Bridging graph metrics and stability of graph neural networks. NeurIPS, 2022.
  9. Graph transfer learning via adversarial domain adaptation with graph convolution. TKDE, 2022.
  10. Distribution shift mitigation at test time with performance guarantees. arXiv, 2023.
  11. Fakeedge: Alleviate dataset shift in link prediction. In LoG, 2022.
  12. Source-free unsupervised domain adaptation: A survey. arXiv, 2022.
  13. Nes-tl: Network embedding similarity-based transfer learning. TNSE, 2020.
  14. Learning adaptive node embeddings across graphs. TKDE, 2023.
  15. Inductive representation learning on large graphs. NeurIPS, 2017.
  16. Diva: Domain invariant variational autoencoders. In MIDL, 2020.
  17. Empowering graph representation learning with test-time graph transformation. ICLR, 2023.
  18. Graphpatcher: Mitigating degree bias for graph neural networks via test-time augmentation. NeurIPS, 2023.
  19. Semi-supervised classification with graph convolutional networks. ICLR, 2017.
  20. Fair node representation learning via adaptive data augmentation. arXiv, 2022.
  21. Patterns of dataset shift. In LMCE, 2014.
  22. Out-of-distribution generalization on graphs: A survey. arXiv, 2022.
  23. A comprehensive survey on test-time adaptation under distribution shifts. arXiv, 2023.
  24. Confidence may cheat: Self-training on graph neural networks under distribution shift. In TheWebConf, 2022.
  25. Structural re-weighting improves graph domain adaptation. In ICML, 2023.
  26. Source free unsupervised graph domain adaptation. WSDM, 2024.
  27. A unifying view on dataset shift in classification. Pattern Recognit, 2012.
  28. Semi-supervised domain adaptation in graph transfer learning. IJCAI, 2023.
  29. Graphon neural networks and the transferability of graph neural networks. NeurIPS, 2020.
  30. Adversarial deep network embedding for cross-network node classification. In AAAI, 2020.
  31. Network together: Node classification via cross-network deep network embedding. TNNLS, 2020.
  32. Improving graph domain adaptation with network hierarchy. In CIKM, 2023.
  33. Graph prompt learning: A comprehensive survey and beyond. arXiv, 2023.
  34. Test-time training for graph neural networks. arXiv, 2022.
  35. Distribution consistency based self-training for graph neural networks with sparse labels. WSDM, 2024.
  36. Simplifying graph convolutional networks. In ICML, 2019.
  37. Domain-adversarial graph neural networks for text classification. In ICDM, 2019.
  38. Unsupervised domain adaptive graph convolutional networks. In TheWebConf, 2020.
  39. Reinforced sample selection for graph neural networks transfer learning. In BIBM, 2022.
  40. Knowledge distillation improves graph structure augmentation for graph neural networks. NeurIPS, 2022.
  41. Handling distribution shifts on graphs: An invariance perspective. ICLR, 2022.
  42. Non-iid transfer learning on graphs. In AAAI, 2023.
  43. A survey of pretraining on graphs: Taxonomy, methods, and applications. arXiv, 2022.
  44. Predicting positive and negative links in signed social networks by transfer learning. In TheWebConf, 2013.
  45. From local structures to size generalization in graph neural networks. In ICML, 2021.
  46. Graph domain adaptation via theory-grounded spectral regularization. In ICLR, 2023.
  47. A comprehensive survey on source-free domain adaptation. arXiv, 2023.
  48. Dane: Domain adaptive network embedding. IJCAI, 2019.
  49. Adversarial separation network for cross-network node classification. In CIKM, 2021.
  50. Fine-tuning graph neural networks via graph topology induced optimal transport. In IJCAI, 2022.
  51. Adding conditional control to text-to-image diffusion models. In ICCV, 2023.
  52. On learning invariant representations for domain adaptation. In ICML, 2019.
  53. Graphglow: Universal and generalizable structure learning for graph neural networks. KDD, 2023.
  54. Gnnevaluator: Evaluating gnn performance on unseen graphs without labels. NeurIPS, 2023.
  55. Online gnn evaluation under test-time graph distribution shifts. ICLR, 2024.
  56. Shift-robust gnns: Overcoming the limitations of localized graph training data. NeurIPS, 2021.
  57. Transfer learning of graph neural networks with ego-graph information maximization. NeurIPS, 2021.
  58. Shift-robust node classification via graph adversarial clustering. NeurIPS, 2022.
  59. Explaining and adapting graph conditional shift. arXiv, 2023.
  60. Graphcontrol: Adding conditional control to universal graph pre-trained models for graph domain transfer learning. arXiv, 2023.
  61. A comprehensive survey on transfer learning. Proc. IEEE, 2020.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets