An adversarial variational graph autoencoder with contrastive learning for robust anomaly detection in large scale attributed networks

Today's article comes from the Journal of Big Data . The authors are Khan et al., from the Symbiosis Institute of Technology, in India. In this paper, they present a graph anomaly detection framework that combines three ideas: adversarial variational graph autoencoders, attention-based residual modeling, and contrastive learning.

DOI: 10.1186/s40537-025-01342-z