Asynchronous federated learning on heterogeneous devices: A survey

被引:74
作者
Xu, Chenhao [1 ]
Qu, Youyang [2 ,3 ]
Xiang, Yong [1 ]
Gao, Longxiang [2 ,3 ]
机构
[1] Deakin Univ, Sch Informat Technol, Geelong, Vic, Australia
[2] Qilu Univ Technol, Shandong Acad Sci, Key Lab Comp Power Network & Informat Secur, Minist Educ,Shandong Comp Sci Ctr, Jinan, Peoples R China
[3] Shandong Fundamental Res Ctr Comp Sci, Shandong Prov Key Lab Comp Networks, Jinan, Peoples R China
基金
国家重点研发计划; 澳大利亚研究理事会;
关键词
Asynchronous federated learning; Device heterogeneity; Data heterogeneity; Privacy; Security; DIFFERENTIAL PRIVACY; INTERNET; ALGORITHM; FRAMEWORK; NETWORKS;
D O I
10.1016/j.cosrev.2023.100595
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Federated learning (FL) is a kind of distributed machine learning framework, where the global model is generated on the centralized aggregation server based on the parameters of local models, addressing concerns about privacy leakage caused by the collection of local training data. With the growing computational and communication capacities of edge and IoT devices, applying FL on heterogeneous devices to train machine learning models is becoming a prevailing trend. Nonetheless, the synchronous aggregation strategy in the classic FL paradigm, particularly on heterogeneous devices, encounters limitations in resource utilization due to the need to wait for slow devices before aggregation in each training round. Furthermore, the uneven distribution of data across devices (i.e. data heterogeneity) in real-world scenarios adversely impacts the accuracy of the global model. Consequently, many asynchronous FL (AFL) approaches have been introduced across various application contexts to enhance efficiency, performance, privacy, and security. This survey comprehensively analyzes and summarizes existing AFL variations using a novel classification scheme, including device heterogeneity, data heterogeneity, privacy, and security on heterogeneous devices, as well as applications on heterogeneous devices. Finally, this survey reveals rising challenges and presents potentially promising research directions in this under-investigated domain.
引用
收藏
页数:15
相关论文
共 127 条
[1]  
Abdel-Basset M., 2022, Deep Learning Techniques for IoT Security and Privacy, P215
[2]   The General Data Protection Regulation in the Age of Surveillance Capitalism [J].
Andrew, Jane ;
Baker, Max .
JOURNAL OF BUSINESS ETHICS, 2021, 168 (03) :565-578
[3]  
Anguita D., 2013, ESANN, V3, P3
[4]  
Armknecht F., 2015, 20151192 CRYPT EPRIN
[5]  
Avdyukhin D, 2021, PR MACH LEARN RES, V139
[6]  
Cao P, **DATA OBJECT**, DOI 10.6084/m9.figshare.6127874.v1
[7]  
Cao XY, 2021, PROCEEDINGS OF THE 30TH USENIX SECURITY SYMPOSIUM, P947
[8]  
Chai Z, 2021, Arxiv, DOI arXiv:2010.05958
[9]   FedSA: A staleness-aware asynchronous Federated Learning algorithm with non-IID data [J].
Chen, Ming ;
Mao, Bingcheng ;
Ma, Tianyi .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2021, 120 :1-12
[10]  
Chen TY, 2020, Arxiv, DOI arXiv:2007.06081