计算机应用研究2025，Vol.42Issue(1)：125-132,8.DOI:10.19734/j.issn.1001-3695.2024.06.0205
基于相似性的个性化联邦学习模型聚合框架
Similarity-based personalized federated learning model aggregation framework
摘要
Abstract
In traditional federated learning,global model obtained through weighted aggregation cannot address the issue of cross-client data heterogeneity.Existing research addresses the problem by forming personalized models,but balancing the global common information and local personality information remains a challenge.In response to the above problems,this pa-per proposed FedPG,a personalized federated learning model aggregation framework.Based on the similarity of the client models,FedPG used the cosine similarity of the normalized model parameter changes as the personalized weight of model aggregation,thereby realizing personalized client-oriented global model aggregation.By introducing a smoothing coefficient,this framework could flexibly adjust the proportion of common and personalized information in the model.To reduce the cost of selecting the smoothing coefficient,this paper further proposed the FedPGS framework,which scheduled the smoothing coeffi-cient.In the experiments,the FedPG and FedPGS frameworks improve the accuracy of the FedAvg,FedProto,and FedProx algorithms on datasets with feature distribution shift by an average of 1.20 to 11.50 percentage points,and reduce the impact of malicious devices on model accuracy.The results indicate that the FedPG and FedPGS frameworks can effectively enhance model accuracy and robustness in scenarios with data heterogeneity and malicious device interference.关键词
个性化联邦学习/余弦相似度/数据异构/模型聚合/恶意设备Key words
personalized federated learning/cosine similarity/data heterogeneity/model aggregation/malicious device分类
信息技术与安全科学引用本文复制引用
武文媗,王灿,黄静静,吴秋新,秦宇..基于相似性的个性化联邦学习模型聚合框架[J].计算机应用研究,2025,42(1):125-132,8.基金项目
国家自然科学基金资助项目(61604014) （61604014）
未来区块链与隐私计算高精尖项 目(GJJ-23) （GJJ-23）
北京信息科技大学"青年骨干教师"支持计划项目(YBT202450) （YBT202450）
