mlsanityData to 7 Oct 2026

Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learning

arXiv 2402.16374 ↗First posted 26 Feb 2024cs.LG cs.SIcited by 17

Not on the map. Why?

Abstract (arXiv)

Graph learning plays a pivotal role and has gained significant attention in various application scenarios, from social network analysis to recommendation systems, for its effectiveness in modeling complex data relations represented by graph structural data. In reality, the real-world graph data typically show dynamics over time, with changing node attributes and edge structure, leading to the severe graph data distribution shift issue. This issue is compounded by the diverse and complex nature of distribution shifts, which can significantly impact the performance of graph learning methods in degraded generalization and adaptation capabilities, posing a substantial challenge to their effectiveness. In this survey, we provide a comprehensive review and summary of the latest approaches, strategies, and insights that address distribution shifts within the context of graph learning. Concretely, according to the observability of distributions in the inference stage and the availability of sufficient supervision information in the training stage, we categorize existing graph learning methods into several essential scenarios, including graph domain adaptation learning, graph out-of-distribution learning, and graph continual learning. For each scenario, a detailed taxonomy is proposed, with specific descriptions and discussions of existing progress made in distribution-shifted graph learning. Additionally, we discuss the potential applications and future directions for graph learning under distribution shifts with a systematic analysis of the current state in this field. The survey is positioned to provide general guidance for the development of effective graph learning algorithms in handling graph distribution shifts, and to stimulate future research and advancements in this area.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 86 of its 124 references that are in the map. First posted on arXiv 26 Feb 2024.

Builds on

86 of 124 references.

References · 86

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2016Learning without Forgettingcited by 2,465
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  4. 2016Progressive Neural Networkscited by 1,332
  5. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  6. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  8. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  9. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  10. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  11. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  12. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
38 more
  1. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  2. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  3. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  4. 2020Data Augmentation for Graph Neural Networkscited by 200
  5. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  6. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  7. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  8. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  9. 2021Graph Learning: A Surveycited by 140
  10. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  11. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  12. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  13. 2023PRODIGY: Enabling In-context Learning Over Graphscited by 97
  14. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  15. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 93
  16. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  17. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  18. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  19. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  20. 2021Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalizationcited by 70
  21. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  22. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  23. 2017Open-World Knowledge Graph Completioncited by 64
  24. 2020Streaming Graph Neural Networks via Continual Learningcited by 63
  25. 2020Progressive Graph Learning for Open-Set Domain Adaptationcited by 56
  26. 2018Stable Prediction across Unknown Environmentscited by 55
  27. 2022Multimodal learning with graphscited by 54
  28. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  29. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  30. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  31. 2020GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systemscited by 42
  32. 2021TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learningcited by 42
  33. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  34. 2021Graph Few-shot Class-incremental Learningcited by 40
  35. 2020Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19cited by 38
  36. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  37. 2023Continual Learning on Dynamic Graphs via Parameter Isolationcited by 35
  38. 2019AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphscited by 32

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 4.

17 papers.

Sort:

By area:

  1. 2025Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesicscited by 17
  2. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  3. 2024Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformationcited by 15
  4. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 13
  5. 2024Online GNN Evaluation Under Test-time Graph Distribution Shiftscited by 12
  6. 2026USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptationcited by 9
  7. 2025GCAL: Adapting Graph Models to Evolving Domain Shiftscited by 8
  8. 2026DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptationcited by 4
  9. 2026DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptationcited by 2
  10. 2024Conditional Shift-Robust Conformal Prediction for Graph Neural Networkcited by 1
  11. 2025Cross-Domain Graph Anomaly Detection via Test-Time Training with Homophily-Guided Self-Supervisioncited by 1
  12. 2025M2LLM: Multi-view Molecular Representation Learning with Large Language Modelscited by 1
5 more
  1. 2026Cross-Resolution Semantic Learning for Graph Domain Adaptationcited by 1
  2. 2025Out-of-Distribution Graph Models Mergingcited by 0
  3. 2025Robust OOD Graph Learning via Mean Constraints and Noise Reductioncited by 0
  4. 2025Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmarkcited by 0
  5. 2025Dynamic Mixture-of-Experts for Incremental Graph Learningcited by 0