Label-based Graph Augmentation with Metapath for Graph Anomaly Detection

arXiv:2308.10918v2 Announce Type: replace
Abstract: Graph anomaly detection has attracted considerable attention from various domain ranging from network security to finance in recent years. Due to the fact that labeling is very costly, existing methods are predominately developed in an unsupervised manner. However, the detected anomalies may be found out uninteresting instances due to the absence of prior knowledge regarding the anomalies looking for. This issue may be solved by using few labeled anomalies as prior knowledge. In real-world scenarios, …

anomaly anomaly detection arxiv augmentation cs.ai cs.lg detection graph type