mlsanityData to 7 Oct 2026

Graph Information Bottleneck

arXiv 2010.12811 ↗First posted 24 Oct 2020cs.LG stat.MLcited by 168

Not on the map. Why?

Abstract (arXiv)

Representation learning of graph-structured data is challenging because both graph structure and node features carry important information. Graph Neural Networks (GNNs) provide an expressive way to fuse information from network structure and node features. However, GNNs are prone to adversarial attacks. Here we introduce Graph Information Bottleneck (GIB), an information-theoretic principle that optimally balances expressiveness and robustness of the learned representation of graph-structured data. Inheriting from the general Information Bottleneck (IB), GIB aims to learn the minimal sufficient representation for a given task by maximizing the mutual information between the representation and the target, and simultaneously constraining the mutual information between the representation and the input data. Different from the general IB, GIB regularizes the structural as well as the feature information. We design two sampling algorithms for structural regularization and instantiate the GIB principle with two new models: GIB-Cat and GIB-Bern, and demonstrate the benefits by evaluating the resilience to adversarial attacks. We show that our proposed models are more robust than state-of-the-art graph defense models. GIB-based models empirically achieve up to 31% improvement with adversarial perturbation of the graph structure as well as node features.

Key facts. Cited by 168 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 26; 2023: 39; 2024: 32; 2025: 33; 2026: 19.

168 papers.

Sort:

By area:

  1. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  2. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  3. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  4. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  5. 2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
  6. 2021Robustness of Graph Neural Networks at Scalecited by 100
  7. 2021Beltrami Flow and Neural Diffusion on Graphscited by 84
  8. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  9. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
  10. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  11. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  12. 2023Are Defenses for Graph Neural Networks Robust?cited by 38
38 more
  1. 2023Variational Positive-incentive Noise: How Noise Benefits Modelscited by 38
  2. 2023SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimizationcited by 35
  3. 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modelingcited by 35
  4. 2022EIGNN: Efficient Infinite-Depth Graph Neural Networkscited by 32
  5. 2024TimeX++: Learning Time-Series Explanations with Information Bottleneckcited by 32
  6. 2022DropMessage: Unifying Random Dropping for Graph Neural Networkscited by 29
  7. 2023Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalizationcited by 29
  8. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  9. 2021PAC-Bayes Information Bottleneckcited by 28
  10. 2022Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentationscited by 28
  11. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
  12. 2023Conditional Graph Information Bottleneck for Molecular Relational Learningcited by 24
  13. 2023Graph Information Bottleneck for Remote Sensing Segmentationcited by 24
  14. 2023Interpretable Prototype-based Graph Information Bottleneckcited by 23
  15. 2021Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsitycited by 20
  16. 2022Compact Graph Structure Learning via Mutual Information Compressioncited by 20
  17. 2022Self-Supervised Graph Structure Refinement for Graph Neural Networkscited by 20
  18. 2024EXGC: Bridging Efficiency and Explainability in Graph Condensationcited by 20
  19. 2023Drug Discovery with Dynamic Goal-aware Fragmentscited by 19
  20. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18
  21. 2024FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Predictioncited by 18
  22. 2022BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneckcited by 17
  23. 2024GOODAT: Towards Test-time Graph Out-of-Distribution Detectioncited by 17
  24. 2021AI Ethics Statements -- Analysis and lessons learnt from NeurIPS Broader Impact Statementscited by 16
  25. 2023Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modelingcited by 16
  26. 2023On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximationcited by 16
  27. 2024SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detectioncited by 16
  28. 2024An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generationcited by 16
  29. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  30. 2022Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clusteringcited by 15
  31. 2023Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalizationcited by 15
  32. 2023Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labelingcited by 15
  33. 2022GraphTTA: Test Time Adaptation on Graph Neural Networkscited by 14
  34. 2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
  35. 2023A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacycited by 14
  36. 2021GraphFM: Graph Factorization Machines for Feature Interaction Modelingcited by 13
  37. 2023Explainable Spatio-Temporal Graph Neural Networkscited by 13
  38. 2023A Generalized Neural Diffusion Framework on Graphscited by 13

50 most cited of 168 All 168 (JSON)