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: Zade, H.R., Zare, H., Ghassemi Parsa, M., Davardoust, H., Bagheri, M.S. (2025). DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction. In: Cherifi, H., Donduran, M., Rocha, L.M., Cherifi, C., Varol, O. (eds) Complex Networks & Their Applications XIII. COMPLEX NETWORKS 2024 2024. Studies in Computational Intelligence, vol 1189. Springer, Cham. https://doi.org/10.1007/978-3-031-82435-7_1
Download Paper