Conference
Open access
Sep 2026
FedUP: Uncertainty-Aware Personalized Federated Learning via Probabilistic Prototypes
FedUP is an uncertainty-aware personalized federated learning framework that models prototypes as probability distributions and aggregates prototype distributions through reliability-informed barycenters on the statistical manifold, suppressing unreliable contributions while preserving geometric structure.
Fu Qi, Weishan Zhang, Ling-Zhao Meng et al.
· Proceedings of the Thirty-Fi... · 0 citations