自动化学报2023，Vol.49Issue(12)：2493-2506,14.DOI:10.16383/j.aas.c201018
面向非独立同分布数据的自适应联邦深度学习算法
Adaptive Federated Deep Learning With Non-IID Data
摘要
Abstract
In recent years,federated learning(FL)that can break data barriers and realize the value of isolated data,has been received wide-spread attention from industry and academia.However,in real industry applications,federated learning has problems with privacy leakage and model accuracy loss,which is analyzed through mathem-atical demonstration in this study.To solve the issues,this paper proposes an adaptive global model aggregation scheme that can adaptively set the Mini-batch value of each participant and the global model aggregation interval for the parameter server,which aims to improve the training efficiency while ensuring the accuracy of the model.Moreover,this paper introduces the chaos system into the federated learning field,which is used to construct a hy-brid privacy-preserving scheme based on chaos system and homomorphic encryption,thereby further improving the privacy protection level.Theoretical analysis and experimental results show that the proposed approach can guaran-tee the data privacy security of participants.Moreover,in the non-independent and identically distributed(Non-IID)data scenario,the proposed method can improve the training efficiency and reduce communication cost while ensuring the model accuracy,which is feasible for real industrial applications.关键词
联邦学习/深度学习/隐私保护/同态加密/混沌系统Key words
Federated learning(FL)/deep learning/privacy-preserving/homomorphic encryption/chaos system引用本文复制引用
张泽辉,李庆丹,富瑶,何宁昕,高铁杠..面向非独立同分布数据的自适应联邦深度学习算法[J].自动化学报,2023,49(12):2493-2506,14.基金项目
国家科技重大专项基金(2018YFB0204304),天津市研究生科研创新基金(2019YJSB067)资助Supported by National Science and Technology Major Project of China(2018YFB0204304)and Tianjin Research Innovation Project for Postgraduate Students(2019YJSB067) （2018YFB0204304）
