典型文献
Mp Fed con:Model-Contrastive Personalized Federated Learning with the Class Center
文献摘要：
Federated learning is an emerging distributed privacy-preserving framework in which parties are trained collaboratively by sharing model or gradient updates instead of sharing private data.However,the heterogeneity of local data distribution poses a significant challenge.This paper focuses on the label distribution skew,where each party can only access a partial set of the whole class set.It makes global updates drift while aggregating these bi-ased local models.In addition,many studies have shown that deep leakage from gradients endangers the reliability of federated learn-ing.To address these challenges,this paper propose a new person-alized federated learning method named MpFedcon.It addresses the data heterogeneity problem and privacy leakage problem from global and local perspectives.Our extensive experimental results demonstrate that MpFedcon yields effective resists on the label leakage problem and better performance on various image classifi-cation tasks,robust in partial participation settings,non-iid data,and heterogeneous parties.
文献关键词：
中图分类号：
作者姓名：
LI Xingchen;FANG Zhijun;SHI Zhicai
作者机构：
School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China
文献出处：
引用格式：
[1]LI Xingchen;FANG Zhijun;SHI Zhicai-.Mp Fed con:Model-Contrastive Personalized Federated Learning with the Class Center)[J].武汉大学自然科学学报（英文版）,2022(06):508-520
A类：
ased,MpFedcon,iid
B类：
Model,Contrastive,Personalized,Federated,Learning,Class,Center,learning,emerging,distributed,privacy,preserving,framework,which,parties,are,trained,collaboratively,by,sharing,updates,instead,private,data,However,heterogeneity,local,distribution,poses,significant,This,paper,focuses,label,skew,where,each,party,only,access,partial,whole,It,makes,global,drift,while,aggregating,these,models,In,addition,many,studies,have,shown,that,deep,leakage,from,gradients,endangers,reliability,federated,To,challenges,this,propose,new,person,method,named,addresses,problem,perspectives,Our,extensive,experimental,results,demonstrate,yields,effective,resists,better,performance,various,image,classifi,cation,tasks,robust,participation,settings,heterogeneous
AB值：
0.6099
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
