Open access
2026
Edge- Federated Graph Anomaly Detection With Self-Supervised Representation Learning for IoT Networks
This paper presents an Edge Federated Graph Anomaly Detection (E-FGAD) framework for IoT environments that combines centralized self-supervised pre-training with distributed supervised learning over edge embeddings that outperforms centralized and federated baselines in detecting attacks while preserving privacy.
Nuha A. Hamad, Khairul Azmi Abu Bakar, Faizan Qamar et al.
· IEEE Access · 0 citations