Robust Design of Federated Learning for Edge-Intelligent Networks

被引:7
作者
Qi, Qiao [1 ,2 ,3 ]
Chen, Xiaoming [1 ,2 ,3 ]
机构
[1] Zhejiang Univ, Coll Informat Sci & Elect Engn, Hangzhou 310027, Peoples R China
[2] Zhejiang Prov Key Lab Informat Proc Commun & Netw, Hangzhou 310007, Peoples R China
[3] Zhejiang Univ, Int Joint Innovat Ctr, Haining 314400, Peoples R China
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
Atmospheric modeling; Computational modeling; Data models; Performance evaluation; Downlink; Uplink; Training; Edge-intelligent networks; federated learning; resource allocation; robust design;
D O I
10.1109/TCOMM.2022.3175921
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Mass data traffics, low-latency wireless services and advanced artificial intelligence (AI) technologies have driven the emergence of a new paradigm for wireless networks, namely edge-intelligent networks, which are more efficient and flexible than traditional cloud-intelligent networks. Considering users' privacy, model sharing-based federated learning (FL) that migrates model parameters but not private data from edge devices to a central cloud is particularly attractive for edge-intelligent networks. Due to multiple rounds of iterative updating of high-dimensional model parameters between base station (BS) and edge devices, the communication reliability is a critical issue of FL for edge-intelligent networks. We reveal the impacts of the errors generated during model broadcast and model aggregation via wireless channels caused by channel fading, interference and noise on the accuracy of FL, especially when there exists channel uncertainty. To alleviate the impacts, we propose a robust FL algorithm for edge-intelligent networks with channel uncertainty, which is formulated as a worst-case optimization problem with joint device selection and transceiver design. Finally, simulation results validate the robustness and effectiveness of the proposed algorithm.
引用
收藏
页码:4469 / 4481
页数:13
相关论文
共 42 条
[1]  
Abari O, 2016, Arxiv, DOI arXiv:1612.02307
[2]  
Acar DAE, 2021, Arxiv, DOI arXiv:2111.04263
[3]   Convergence of Federated Learning Over a Noisy Downlink [J].
Amiri, Mohammad Mohammadi ;
Gunduz, Deniz ;
Kulkarni, Sanjeev R. ;
Poor, H. Vincent .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (03) :1422-1437
[4]   Federated Learning Over Wireless Fading Channels [J].
Amiri, Mohammad Mohammadi ;
Gunduz, Deniz .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (05) :3546-3557
[5]  
[Anonymous], 2011, COORDINATED MULTIPOI
[6]  
Ben-Tal A., 2001, MPS-SIAM Series on Optimization
[7]  
Bezdek J. C., 2003, Neural, Parallel & Scientific Computations, V11, P351
[8]  
Boyd S., 2004, CONVEX OPTIMIZATION
[9]   Optimized Power Control for Over-the-Air Computation in Fading Channels [J].
Cao, Xiaowen ;
Zhu, Guangxu ;
Xu, Jie ;
Huang, Kaibin .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (11) :7498-7513
[10]   A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks [J].
Chen, Mingzhe ;
Yang, Zhaohui ;
Saad, Walid ;
Yin, Changchuan ;
Poor, H. Vincent ;
Cui, Shuguang .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2021, 20 (01) :269-283