mlsanityData to 7 Oct 2026

Graphs Generalization under Distribution Shifts

arXiv 2403.16334 ↗First posted 25 Mar 2024cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Traditional machine learning methods heavily rely on the independent and identically distribution assumption, which imposes limitations when the test distribution deviates from the training distribution. To address this crucial issue, out-of-distribution (OOD) generalization, which aims to achieve satisfactory generalization performance when faced with unknown distribution shifts, has made a significant process. However, the OOD method for graph-structured data currently lacks clarity and remains relatively unexplored due to two primary challenges. Firstly, distribution shifts on graphs often occur simultaneously on node attributes and graph topology. Secondly, capturing invariant information amidst diverse distribution shifts proves to be a formidable challenge. To overcome these obstacles, in this paper, we introduce a novel framework, namely Graph Learning Invariant Domain genERation (GLIDER). The goal is to (1) diversify variations across domains by modeling the potential seen or unseen variations of attribute distribution and topological structure and (2) minimize the discrepancy of the variation in a representation space where the target is to predict semantic labels. Extensive experiment results indicate that our model outperforms baseline methods on node-level OOD generalization across domains in distribution shift on node features and topological structures simultaneously.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

33 of 38 references.

References · 33

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2019Invariant Risk Minimizationcited by 1,832
  5. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  7. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  8. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  9. 2021Domain Generalization: A Surveycited by 760
  10. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  11. 2013Domain Generalization via Invariant Feature Representationcited by 622
  12. 2018Disentangling by Factorisingcited by 614
21 more
  1. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  2. 2019Multi-scale Attributed Node Embeddingcited by 543
  3. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  4. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  5. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  6. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  7. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  8. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  9. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  10. 2021Model-Based Domain Generalizationcited by 103
  11. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  12. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  13. 2020Sample Efficient Reinforcement Learning with REINFORCEcited by 85
  14. 2020On the Transfer of Disentangled Representations in Realistic Settingscited by 63
  15. 2020Learning Causal Semantic Representation for Out-of-Distribution Predictioncited by 60
  16. 2020Robust Optimization as Data Augmentation for Large-scale Graphscited by 58
  17. 2020Active Invariant Causal Prediction: Experiment Selection through Stabilitycited by 37
  18. 2022Metropolis-Hastings Data Augmentation for Graph Neural Networkscited by 30
  19. 2020Stable Adversarial Learning under Distributional Shiftscited by 16
  20. 2020Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalizationcited by 14
  21. 2024Learning Invariant Representations of Graph Neural Networks via Cluster Generalizationcited by 10

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Dissecting the Failure of Invariant Learning on Graphscited by 5
  2. 2024Generalization of Graph Neural Networks is Robust to Model Mismatchcited by 4
  3. 2024Hypergraph-Based Dynamic Graph Node Classificationcited by 1