mlsanityData to 7 Oct 2026

Graph Structure Learning with Variational Information Bottleneck

arXiv 2112.08903 ↗First posted 16 Dec 2021cs.LG cs.AIcited by 81

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL advances the Information Bottleneck (IB) principle for graph structure learning, providing a more elegant and universal framework for mining underlying task-relevant relations. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks. VIB-GSL deduces a variational approximation for irregular graph data to form a tractable IB objective function, which facilitates training stability. Extensive experimental results demonstrate that the superior effectiveness and robustness of VIB-GSL.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

27 of 41 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  7. 2016Deep Variational Information Bottleneckcited by 915
  8. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  9. 2018MINE: Mutual Information Neural Estimationcited by 680
  10. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  11. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  12. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 213
15 more
  1. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  2. 2020Graph Information Bottleneckcited by 168
  3. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  4. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  5. 2017Network Representation Learning: A Surveycited by 101
  6. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  7. 2021Variational Information Bottleneck for Effective Low-Resource Fine-Tuningcited by 51
  8. 2021Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networkscited by 38
  9. 2020Learning Optimal Representations with the Decodable Information Bottleneckcited by 32
  10. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  11. 2020Diversity inducing Information Bottleneck in Model Ensemblescited by 27
  12. 2020Disentangled Information Bottleneckcited by 24
  13. 2021Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Explorationcited by 15
  14. 2021Disentangled Variational Information Bottleneck for Multiview Representation Learningcited by 8
  15. 2019Information-Bottleneck Approach to Salient Region Discoverycited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 14; 2023: 24; 2024: 20; 2025: 17; 2026: 6.

81 papers.

Sort:

By area:

  1. 2023How Does Information Bottleneck Help Deep Learning?cited by 92
  2. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  3. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  4. 2023GSLB: The Graph Structure Learning Benchmarkcited by 49
  5. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  6. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  7. 2024A Comprehensive Survey on Data Augmentationcited by 38
  8. 2022Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detectioncited by 35
  9. 2023SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimizationcited by 35
  10. 2022Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashingcited by 31
  11. 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learningcited by 30
  12. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
38 more
  1. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  2. 2023Conditional Graph Information Bottleneck for Molecular Relational Learningcited by 24
  3. 2023Interpretable Prototype-based Graph Information Bottleneckcited by 23
  4. 2023Data-centric Graph Learning: A Surveycited by 22
  5. 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
  6. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  7. 2025Edge Prompt Tuning for Graph Neural Networkscited by 18
  8. 2024GOODAT: Towards Test-time Graph Out-of-Distribution Detectioncited by 17
  9. 2023Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modelingcited by 16
  10. 2023A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacycited by 14
  11. 2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspectivecited by 14
  12. 2022ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splittingcited by 13
  13. 2022Representation Learning in Deep RL via Discrete Information Bottleneckcited by 13
  14. 2023RDGSL: Dynamic Graph Representation Learning with Structure Learningcited by 13
  15. 2024SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendationcited by 12
  16. 2025A Survey of Graph Transformers: Architectures, Theories and Applicationscited by 12
  17. 2022A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneckcited by 10
  18. 2024Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awarenesscited by 10
  19. 2022Curvature Graph Generative Adversarial Networkscited by 9
  20. 2022Finding Diverse and Predictable Subgraphs for Graph Domain Generalizationcited by 9
  21. 2023UGSL: A Unified Framework for Benchmarking Graph Structure Learningcited by 9
  22. 2023Latent Graph Inference with Limited Supervisioncited by 9
  23. 2023Combating Bilateral Edge Noise for Robust Link Predictioncited by 9
  24. 2025Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flowcited by 9
  25. 2022Self-organization Preserved Graph Structure Learning with Principle of Relevant Informationcited by 8
  26. 2024Mitigating Propensity Bias of Large Language Models for Recommender Systemscited by 8
  27. 2024DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Modelscited by 8
  28. 2025GCAL: Adapting Graph Models to Evolving Domain Shiftscited by 8
  29. 2026VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneckcited by 8
  30. 2023Poincar'e Differential Privacy for Hierarchy-Aware Graph Embeddingcited by 7
  31. 2024Deep Contrastive Graph Learning with Clustering-Oriented Guidancecited by 7
  32. 2022Heterogeneous Graph Neural Network for Privacy-Preserving Recommendationcited by 6
  33. 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margincited by 6
  34. 2024Dynamic Graph Information Bottleneckcited by 5
  35. 2023Robust Ante-hoc Graph Explainer using Bilevel Optimizationcited by 4
  36. 2024Graph Augmentation for Recommendationcited by 4
  37. 2024Discrete Curvature Graph Information Bottleneckcited by 4
  38. 2024PhoGAD: Graph-based Anomaly Behavior Detection with Persistent Homology Optimizationcited by 3

50 most cited of 81 All 81 (JSON)