Dynamic Graph Information Bottleneck
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 DGIB$_{MS}$ and DGIB$_C$, in which the DGIB$_{MS}$ channel aims to learn the minimal and sufficient representations, with the DGIB$_{MS}$ 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.
Code (1)
Tasks
Link PredictionRepresentation LearningSimilar Papers 제목 키워드 기반
Graph Neural Network-State Predictive Information Bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kinetics
Molecular dynamics simulations offer detailed insights into atomic motions but face timescale limitations. Enhanced sampling methods have addressed these challenges but even with machine learning, they often rely on pre-…
Graph Neural NetworkGraph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
Temporal graph learning is crucial for dynamic networks where nodes and edges evolve over time and new nodes continuously join the system. Inductive representation learning in such settings faces two major challenges: ef…
Graph structure learningRepresentation LearningGraph LearningOptimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Supervised Learning Approach
Seizure detection from EEG signals is highly challenging due to complex spatiotemporal dynamics and extreme inter-patient variability. To model them, recent methods construct dynamic graphs via statistical correlations, …
Self-Supervised LearningRepresentation LearningSeizure DetectionBottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU
Dynamic graph neural network (DGNN) is becoming increasingly popular because of its widespread use in capturing dynamic features in the real world. A variety of dynamic graph neural networks designed from algorithmic per…
CPUDiversityGPUGraph Neural NetworkSelf-Explainable Temporal Graph Networks based on Graph Information Bottleneck
Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGN…
Link PredictionPrediction