网络与信息安全学报2024，Vol.10Issue(6)：1-23,23.DOI:10.11959/j.issn.2096-109x.2024077
联邦学习通信优化方法综述
Review of communication optimization methods in federated learning
摘要
Abstract
With the development and popularization of artificial intelligence technologies represented by deep learning,the security issues they continuously expose have become a huge challenge affecting cyberspace secu-rity.Traditional cloud-centric distributed machine learning,which trains models or optimizes model perfor-mance by collecting data from participating parties,is susceptible to security attacks and privacy attacks during the data exchange process,leading to consequences such as a decline in overall system efficiency or the leak-age of private data.Federated learning,as a distributed machine learning paradigm with privacy protection ca-pabilities,exchanges model parameters through frequent communication between clients and parameter servers,training a joint model without the raw data leaving the local area.This greatly reduces the risk of private data leakage and ensures data security to a certain extent.However,as deep learning models become larger and fed-erated learning tasks more complex,communication overhead also increases,eventually becoming a barrier to the application of federated learning.Therefore,the exploration of communication optimization methods for federated learning has become a hot topic.The technical background and workflow of federated learning were introduced,and the sources and impacts of its communication bottlenecks were analyzed.Then,based on the factors affecting communication efficiency,existing federated learning communication optimization methods were comprehensively sorted out and analyzed from optimization objectives such as model parameter compres-sion,model update strategies,system architecture,and communication protocols.The development trend of this research field was also presented.Finally,the problems faced by existing federated learning communication op-timization methods were summarized,and future development trends and research directions were looked for-ward to.关键词
联邦学习/边缘计算/通信优化/模型压缩Key words
federated learning/edge computing/communication optimization/model compression分类
信息技术与安全科学引用本文复制引用
杨智凯,刘亚萍,张硕,孙哲,严定宇..联邦学习通信优化方法综述[J].网络与信息安全学报,2024,10(6):1-23,23.基金项目
国家自然科学基金(62372124) （62372124）
广东省重点领域研发计划(2019B010137005) The National Natural Science Foundation of China(62372124),Key-Area Research and Development Pro-gram of Guangdong Province(2019B010137005) （2019B010137005）
