mlsanityData to 7 Oct 2026

Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization

arXiv 2306.15902 ↗First posted 28 Jun 2023cs.LG cs.AI cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) graph generalization are critical for many real-world applications. Existing methods neglect to discard spurious or noisy features of inputs, which are irrelevant to the label. Besides, they mainly conduct instance-level class-invariant graph learning and fail to utilize the structural class relationships between graph instances. In this work, we endeavor to address these issues in a unified framework, dubbed Individual and Structural Graph Information Bottlenecks (IS-GIB). To remove class spurious feature caused by distribution shifts, we propose Individual Graph Information Bottleneck (I-GIB) which discards irrelevant information by minimizing the mutual information between the input graph and its embeddings. To leverage the structural intra- and inter-domain correlations, we propose Structural Graph Information Bottleneck (S-GIB). Specifically for a batch of graphs with multiple domains, S-GIB first computes the pair-wise input-input, embedding-embedding, and label-label correlations. Then it minimizes the mutual information between input graph and embedding pairs while maximizing the mutual information between embedding and label pairs. The critical insight of S-GIB is to simultaneously discard spurious features and learn invariant features from a high-order perspective by maintaining class relationships under multiple distributional shifts. Notably, we unify the proposed I-GIB and S-GIB to form our complementary framework IS-GIB. Extensive experiments conducted on both node- and graph-level tasks consistently demonstrate the superior generalization ability of IS-GIB. The code is available at https://github.com/YangLing0818/GraphOOD.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 49 of its 76 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

49 of 76 references.

References · 49

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2019Invariant Risk Minimizationcited by 1,832
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  12. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
37 more
  1. 2016Deep Variational Information Bottleneckcited by 915
  2. 2020Simple and Deep Graph Convolutional Networkscited by 857
  3. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  4. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  5. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  6. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  7. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  8. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  9. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  10. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  11. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  12. 2020Graph Information Bottleneckcited by 168
  13. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  14. 2020Invariant Rationalizationcited by 131
  15. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  16. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  17. 2020From Local Structures to Size Generalization in Graph Neural Networkscited by 119
  18. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
  19. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  20. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  21. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  22. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  23. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  24. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  25. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  26. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  27. 2021User Preference-aware Fake News Detectioncited by 76
  28. 2019Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentationcited by 74
  29. 2020The Information Bottleneck Problem and Its Applications in Machine Learningcited by 66
  30. 2019Learning Efficient Multi-agent Communication: An Information Bottleneck Approachcited by 60
  31. 2022Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Trainingcited by 56
  32. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  33. 2021Variational Information Bottleneck for Effective Low-Resource Fine-Tuningcited by 51
  34. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  35. 2021Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networkscited by 22
  36. 2021Stable Prediction on Graphs with Agnostic Distribution Shiftcited by 9
  37. 2022Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 5; 2026: 2.

15 papers.

Sort:

  1. 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 101
  2. 2023VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPscited by 34
  3. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  4. 2024How Interpretable Are Interpretable Graph Neural Networks?cited by 13
  5. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  6. 2023Disentangled Representation Learning with Transmitted Information Bottleneckcited by 3
  7. 2024Large Language Models Meet Graph Neural Networks: A Perspective of Graph Miningcited by 3
  8. 2025Generative Risk Minimization for Out-of-Distribution Generalization on Graphscited by 2
  9. 2025Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptationcited by 2
  10. 2025BotTrans: A Multi-Source Graph Domain Adaptation Approach for Social Bot Detectioncited by 1
  11. 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decompositioncited by 1
  12. 2024Improving Graph Out-of-distribution Generalization Beyond Causalitycited by 0
3 more
  1. 2025NodeNAS: Node-Specific Graph Neural Architecture Search for Out-of-Distribution Generalizationcited by 0
  2. 2025General OOD Detection via Model-aware and Subspace-aware Variable Prioritycited by 0
  3. 2026EdgeMask-DG*: Learning Domain-Invariant Graph Structures via Adversarial Edge Maskingcited by 0