期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到1篇文章
< 1 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
pFedUL:Layer-Aware Federated Unlearning for Personalized Federated Learning 认领 引用
1
作者 Zhuodong Liu Xiangyu Li Zhihao Zhang 《Computers, Materials & Continua》 SCIE EI 2026年第9期225-252,共28页
Federated unlearning(FU)enables the removal of specific data contributions from federated learning(FL)models to comply with regulations such as the General Data Protection Regulation(GDPR).However,most existing FU met... Federated unlearning(FU)enables the removal of specific data contributions from federated learning(FL)models to comply with regulations such as the General Data Protection Regulation(GDPR).However,most existing FU methods are designed for the FedAvg paradigm,where all clients share a single global model.In practice,personalized federated learning(pFL)methods such as FedPer,FedRep,Ditto,and FedBN have become widely adopted due to their superior handling of non-IID data.These methods decompose the model into shared global layers and client-specific personalized layers,fundamentally altering the semantics of unlearning,yet this setting has received little attention.We formalize FU under the pFL paradigm,identifying a tension between unlearning completeness on shared layers and personalization preservation for remaining clients.We then propose pFedUL,a layer-aware selective unlearning framework comprising three components:(1)gradient-based layer-wise contribution attribution that separately quantifies the target client’s influence on shared and personalized parameters,(2)adaptive selective unlearning that applies differentiated forgetting strategies across layer types,and(3)a lightweight recalibration protocol enabling remaining clients to restore personalization with minimal overhead.We further introduce two new metrics,Personalization Preservation Score(PPS)and Cross-client Fairness Index(CFI),to evaluate pFL-specific unlearning quality.Experiments on CIFAR-10,CIFAR-100,and FEMNIST under varying non-IID settings indicate that pFedUL achieves unlearning effectiveness comparable to full retraining while maintaining an average of 97.3%personalized accuracy for remaining clients.Compared with six state-of-the-art FU methods adapted to the pFL setting,pFedUL consistently achieves superior personalization preservation,improving over the best existing method by 6.3%in PPS on average with an 8.4×speedup,averaged across all tested pFL architectures and datasets. 展开更多
关键词 Federated learning federated unlearning personalized federated learning machine unlearning layeraware unlearning right to be forgotten
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈