DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction
Published in The 13th International Conference on Complex Networks and their Applications, 2024
In this work, we propose a novel framework that leverages dual reconstruction and contrastive learning to identify anomalies in attributed networks, addressing both structural and attribute-level outliers. Our experiments on benchmark datasets demonstrate significant performance improvements compared to existing methods.
Recommended citation: M Shariat Bagheri, et al. (2024). "DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction." The 13th International Conference on Complex Networks and their Applications.
Download Paper