FedD2S: Personalized Data-Free Federated Knowledge Distillation

arXiv:2402.10846v1 Announce Type: new
Abstract: This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature of client data, often results in suboptimal personalization of a global model compared to locally trained models for each client. To tackle this challenge, we propose a novel approach named FedD2S for Personalized Federated Learning (pFL), leveraging knowledge distillation. FedD2S incorporates a deep-to-shallow layer-dropping mechanism in the data-free knowledge distillation …

abstract arxiv challenge client cs.ai cs.dc cs.lg data distillation drift eess.iv federated learning framework free global issue knowledge model-drift nature paper personalization personalized type