Model layered optimization with contrastive learning for personalized federated learning

In federated learning (FL), the distribution of data across different clients leads to the degradation of global model performance in training. Personalized Federated Learning (pFL) can address this problem through global model personalization. Researches over the past few years have calibrated diff...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Dawei Xu, Chentao Lu, TianXin Chen, Baokun Zheng, Chuan Zhang, Liehuang Zhu, Jian Zhao
Formato:	Artigo
Idioma:	Inglês
Publicado em:	KeAi Communications Co., Ltd. 2025-12-01
coleção:	Digital Communications and Networks
Assuntos:	Federated learning (FL) Personalized federated learning (pFL) Contrastive learning Theoretical analysis
Acesso em linha:	http://www.sciencedirect.com/science/article/pii/S2352864825001439
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!