Jul 2026
Personalized federated learning based on self-excluding aggregation with knowledge distillation
A federated learning framework based on self-excluding aggregation (FedSEA) is proposed by integrating dynamic sparsity-driven client grouping, self-excluding aggregation and cross-group knowledge distillation, which achieves superior performance on the Office-Home and CIFAR-10 datasets.
Wen-Zheng Bi, Wenjun Yu, Li-Hua Gong
· Cluster Computing · 2 citations