计算机工程与应用2024，Vol.60Issue(20)：68-83,16.DOI:10.3778/j.issn.1002-8331.2403-0207
个性化联邦学习的相关方法与展望
Methods and Prospects of Personalized Federated Learning
摘要
Abstract
Currently,with the advancement of artificial intelligence research,artificial intelligence is being widely adopted,and the increasing demand in areas such as data governance has led to growing awareness and concern for privacy protec-tion,this has promoted the popularity of the federated learning(FL)framework.However,existing FL frameworks strug-gle to address heterogeneous issues and personalized user needs.In response to these challenges,methods of personalized federated learning(PFL)are studied and prospects are proposed.Firstly,the FL framework is outlined and its limitations are identified,leading to the research motivation for PFL based on FL scenarios.Subsequently,the analysis of statistical heterogeneity,model heterogeneity,communication heterogeneity,and device heterogeneity in PFL is conducted,and fea-sible solutions are proposed.Then,personalized algorithms in PFL such as client selection and knowledge distillation are categorized,and their innovations and shortcomings are analyzed.Finally,future research directions for PFL are discussed.关键词
个性化联邦学习(PFL)/数据监管/异构问题/隐私保护Key words
personalized federated learning(PFL)/data governance/heterogeneity problems/privacy protection分类
信息技术与安全科学引用本文复制引用
孙艳华,王子航,刘畅,杨睿哲,李萌,王朱伟..个性化联邦学习的相关方法与展望[J].计算机工程与应用,2024,60(20):68-83,16.基金项目
北京市自然科学基金(4222002). （4222002）
