Federated learning as a distributed category yields sub-optimal performance for the presence of Non-iid in multi-domain data. To this end, we proposes a novel clustered federated framework for unsupervised multi-domain network anomaly detection, which implements dynamic clustered federated based on the data distribution of different domain so that each edge user learns the domain-optimized inference model. Compared to baseline, the proposed method enables users to obtain domain-optimal performance.
This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2023-2018-0-01431) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation).