The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation

no code implementations • 21 Jan 2023 • Huancheng Chen, Johnny, Wang, Haris Vikalo

In particular, each client extracts and sends to the server the means of local data representations and the corresponding soft predictions -- information that we refer to as ``hyper-knowledge".

Knowledge Distillation Personalized Federated Learning