Federated Two Stage Decoupling With Adaptive Personalization Layers

no code implementations • 30 Aug 2023 • Hangyu Zhu, Yuxiang Fan, Zhenping Xie

While most existing clustered federated learning methods employ either model gradients or inference outputs as metrics for client partitioning, with the goal of grouping similar devices together, may still have heterogeneity within each cluster.

Clustering Federated Learning