摘要
近年来,联邦学习作为解决数据孤岛问题的技术被广泛关注,已经开始被应用于金融、医疗健康以及智慧城市等领域。从3个层面系统阐述联邦学习算法。首先通过联邦学习的定义、架构、分类以及与传统分布式学习的对比来阐述联邦学习的概念;然后基于机器学习和深度学习对目前各类联邦学习算法进行分类比较和深入分析;最后分别从通信成本、客户端选择、聚合方式优化的角度对联邦学习优化算法进行分类,总结了联邦学习的研究现状,并提出了联邦学习面临的通信、系统异构、数据异构三大难题和解决方案,以及对未来的期望。
In recent years,federated learning has been proposed and received widespread attention to overcome data isolated island challenge.Federated learning related researches were adopted in areas such as financial field,healthcare domain and smart city related application.Federated learning concept was introduced into three different layers.The first layer introduced the definition,architecture,classification of federated learning and compared the federated learning with traditional distributed learning.The second layer presented comparison and analysis of federated learning algorithms from machine learning and deep learning aspects.The third layer separated federated learning optimization algorithms into three aspects to optimize federated learning algorithm through reducing communication cost,selecting proper clients and different aggregation method.Finally,the current research status and three main challenges on communication,heterogeneity of system and data to be solved were concluded,and the future prospects in federated learning domain were proposed.
作者
王健宗
孔令炜
黄章成
陈霖捷
刘懿
何安珣
肖京
WANG Jianzong;KONG Lingwei;HUANG Zhangcheng;CHEN Linjie;LIU Yi;HE Anxun;XIAO Jing(Ping An Technology(Shenzhen)Co.,Ltd.,Shenzhen 518063,China;Ping An Insurance(Group)Company of China,Ltd.,Shenzhen 518031,China)
出处
《大数据》
2020年第6期64-82,共19页
Big Data Research
基金
国家重点研发计划基金资助项目(No.2018YFB1003503,No.2018YFB0204400,No.2017YFB1401202)。
关键词
联邦学习
算法优化
大数据
数据隐私
federated learning
algorithm optimization
big data
data privacy