Litcius/Paper detail

ResGCN: Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks

Yulong Pei, Tianjin Huang, Werner van Ipenburg, Mykola Pechenizkiy

202132 citationsDOIOpen Access PDF

Abstract

Effectively detecting anomalous nodes in attributed networks is crucial for the success of many real-world applications such as fraud and intrusion detection. Existing approaches have difficulties with three major issues: sparsity and nonlinearity capturing, residual modeling, and network smoothing. We propose Residual Graph Convolutional Network (ResGCN), an attention-based deep residual modeling approach that can tackle these issues: modeling the attributed networks with GCN allows to capture the sparsity and nonlinearity, utilizing a deep neural network allows direct residual learning from the input, and a residual-based attention mechanism reduces the adverse effect from anomalous nodes and prevents over-smoothing. Extensive experiments on several real-world attributed networks demonstrate the effectiveness of ResGCN in detecting anomalies.

Topics & Concepts

ResidualComputer scienceSmoothingAnomaly detectionDeep learningArtificial intelligenceConvolutional neural networkGraphNonlinear systemData miningAnomaly (physics)Machine learningAlgorithmTheoretical computer scienceComputer visionQuantum mechanicsPhysicsCondensed matter physicsComplex Network Analysis TechniquesAdvanced Graph Neural NetworksNetwork Security and Intrusion Detection