Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graph
This work addresses anomaly detection in attributed graphs, which is crucial for practical applications, but it appears incremental as it builds on existing self-supervised methods by decoupling components.
The paper tackles the problem of anomaly detection on attributed graphs by addressing semantic mixture and imbalance issues, proposing DSLAD, a self-supervised method that decouples anomaly discrimination and representation learning, which achieves effective results on six benchmark datasets.
Anomaly detection on attributed graphs is a crucial topic for its practical application. Existing methods suffer from semantic mixture and imbalance issue because they mainly focus on anomaly discrimination, ignoring representation learning. It conflicts with the assortativity assumption that anomalous nodes commonly connect with normal nodes directly. Additionally, there are far fewer anomalous nodes than normal nodes, indicating a long-tailed data distribution. To address these challenges, a unique algorithm,Decoupled Self-supervised Learning forAnomalyDetection (DSLAD), is proposed in this paper. DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection. DSLAD employs bilinear pooling and masked autoencoder as the anomaly discriminators. By decoupling anomaly discrimination and representation learning, a balanced feature space is constructed, in which nodes are more semantically discriminative, as well as imbalance issue can be resolved. Experiments conducted on various six benchmark datasets reveal the effectiveness of DSLAD.