Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

arXiv:2604.20596v1 Announce Type: new Abstract: Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user information and thus in practice, it is often coupled with methods such as differential privacy (DP) and s