2024 · 14 citations · 28 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningPredictive AnalyticsDeep LearningGraph AnalyticsGraph MiningGraph-based LearningGraphical RepresentationRepresentation LearningAdversarial RobustnessDynamic Graph LearningDynamic Graph RepresentationGraph Neural NetworksGraph Representation LearningInformation BottleneckInformation Bottleneck AnalysisLink Prediction
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 novelDynamic 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 theMinimal-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 theMSC Condition, we decompose the overall IB objectives into DGIBMS and DGIBC, in which the DGIB_MS channel aims to learn the minimal and sufficient representations, with the DGIBC 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.
28
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
Aldo Pareja, Giacomo Domeniconi, Jie Chen et al. · 2020 · 1.1K citations
Adversarial Attacks on Neural Networks for Graph Data
Daniel Zügner, Amir Akbarnejad, Stephan Günnemann · 2018 · 996 citations · Full text