mlsanityData to 7 Oct 2026

Dynamic Graph Information Bottleneck

arXiv 2402.06716 ↗First posted 9 Feb 2024cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networks (DGNNs) have shown impressive predictive abilities by exploiting the intrinsic dynamics. However, DGNNs exhibit limited robustness, prone to adversarial attacks. This paper presents the novel Dynamic Graph Information Bottleneck (DGIB) framework to learn robust and discriminative representations. Leveraged by the Information Bottleneck (IB) principle, we first propose the expected optimal representations should satisfy the Minimal-Sufficient-Consensual (MSC) Condition. To compress redundant as well as conserve meritorious information into latent representation, DGIB iteratively directs and refines the structural and feature information flow passing through graph snapshots. To meet the MSC Condition, we decompose the overall IB objectives into DGIBMS and DGIBC, in which the DGIBMS channel aims to learn the minimal and sufficient representations, with the DGIBMS channel guarantees the predictive consensus. Extensive experiments on real-world and synthetic dynamic graph datasets demonstrate the superior robustness of DGIB against adversarial attacks compared with state-of-the-art baselines in the link prediction task. To the best of our knowledge, DGIB is the first work to learn robust representations of dynamic graphs grounded in the information-theoretic IB principle.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 9 Feb 2024.

Builds on

33 of 58 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2019Invariant Risk Minimizationcited by 1,832
  8. 2016Variational Graph Auto-Encoderscited by 1,373
  9. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  10. 2016Deep Variational Information Bottleneckcited by 915
  11. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  12. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
21 more
  1. 2019On Variational Bounds of Mutual Informationcited by 550
  2. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  3. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
  4. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  5. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  6. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  7. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
  8. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  9. 2020Graph Information Bottleneckcited by 168
  10. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  11. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  12. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  13. 2020Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphscited by 55
  14. 2023Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classificationcited by 54
  15. 2021Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Networkcited by 52
  16. 2022Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashingcited by 31
  17. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  18. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  19. 2023Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classificationcited by 23
  20. 2023Decoupled Graph Neural Networks for Large Dynamic Graphscited by 14
  21. 2023Poincar'e Differential Privacy for Hierarchy-Aware Graph Embeddingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modelingcited by 35
  2. 2025GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuningcited by 13
  3. 2026A Novel Approach to Temporal QoS Estimation via Extended Kalman Filter-Incorporated Latent Feature Analysiscited by 9
  4. 2025Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problemcited by 5
  5. 2025Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learningcited by 0