Aug 2026
Prototype-based federated learning for one-time soft clustering
Experiments under representative Non-IID settings on benchmark datasets show that PFLS-One achieves improved accuracy and faster convergence compared with representative baseline methods, and the convergence analysis under a non-convex objective provides theoretical support for the proposed method.
Ping Xie, Xiangrui Gao, Jingyan Wu et al.
· Cluster Computing · 0 citations