Graph Anomaly Detection

Graph anomaly detection (GAD) aims to identify unusual patterns—nodes, edges, or subgraphs—within complex network data. Current research heavily utilizes graph neural networks (GNNs), often incorporating contrastive learning, autoencoders, and reinforcement learning to improve anomaly detection accuracy and efficiency, with a growing emphasis on handling noisy labels, multi-view data, and temporal dynamics. GAD's significance lies in its broad applicability across diverse fields, including fraud detection, cybersecurity, and social network analysis, where identifying outliers is crucial for maintaining system integrity and security.