东华大学学报（英文版）2026，Vol.43Issue(1)：41-49,9.DOI:10.19884/j.1672-5220.202412011
FedReg*:应对联邦学习非独立同分布场景下的挑战
FedReg*:Addressing Non-Independent and Identically Distributed Challenges in Federated Learning
石秀金 1朱小龙 1肖文涛1
作者信息
- 1. 东华大学 计算机科学与技术学院,上海 201620
- 折叠
摘要
Abstract
In non-independent and identically distributed(non-IID)data environments,model performance often degrades significantly.To address this issue,two improvement methods are proposed:FedReg and FedReg*.FedReg is a method based on hybrid regularization aimed at enhancing federated learning in non-IID scenarios.It introduces hybrid regularization to replace traditional L2 regularization,combining the advantages of L1 and L2 regularization to enable feature selection while preventing overfitting.This method better adapts to the diverse data distributions of different clients,improving the overall model performance.FedReg* combines hybrid regularization with weighted model aggregation.In addition to the benefits of hybrid regularization,FedReg* applies a weighted averaging method in the model aggregation process,calculating weights based on the cosine similarity between each client gradient and the global gradient to more reasonably distribute client contributions.By considering variations in data quality and quantity among clients,FedReg* highlights the importance of key clients and enhances the model's generalization performance.These improvement methods enhance model accuracy and communication efficiency.关键词
联邦学习/非独立同分布(non-IID)数据/混合正则化/余弦相似度Key words
federated learning/non-independent and identically distributed(non-IID)data/hybrid regularization/cosine similarity分类
信息技术与安全科学引用本文复制引用
石秀金,朱小龙,肖文涛..FedReg*:应对联邦学习非独立同分布场景下的挑战[J].东华大学学报（英文版）,2026,43(1):41-49,9.
