Joint Optimization of Resource Allocation and Data Selection for Fast and Cost-Efficient Federated Edge Learning

被引:1
作者
Jia, Yunjian [1 ]
Huang, Zhen [1 ]
Yan, Jiping [1 ]
Zhang, Yulu [1 ]
Luo, Kun [1 ]
Wen, Wanli [1 ]
机构
[1] Chongqing Univ, Sch Microelect & Commun Engn, Chongqing 400044, Peoples R China
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
mislabeling; Federated edge learning; training cost; resource allocation; data selec- tion; POWER;
D O I
10.1109/TCCN.2024.3424840
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Deploying federated learning at the wireless edge introduces federated edge learning (FEEL). Given FEEL's limited communication resources and potential mislabeled data on devices, improper resource allocation or data selection can hurt convergence speed and increase training costs. Thus, to realize an efficient FEEL system, this paper emphasizes jointly optimizing resource allocation and data selection. Specifically, in this work, through rigorously modeling the training process and deriving an upper bound on FEEL's one-round convergence rate, we establish a problem of joint resource allocation and data selection, which, unfortunately, cannot be solved directly. Toward this end, we equivalently transform the original problem into a solvable form via a variable substitution and then break it into two subproblems, that is, the resource allocation problem and the data selection problem. The two subproblems are mixed-integer non-convex and integer non-convex problems, respectively, and achieving their optimal solutions is a challenging task. Based on the matching theory and applying the convex-concave procedure and gradient projection methods, we devise a low-complexity suboptimal algorithm for the two subproblems, respectively. Finally, the superiority of our proposed scheme of joint resource allocation and data selection is validated by numerical results.
引用
收藏
页码:594 / 606
页数:13
相关论文
共 43 条
[1]   Threshold-Based Data Exclusion Approach for Energy-Efficient Federated Edge Learning [J].
Albaseer, Abdullatif ;
Abdallah, Mohamed ;
Al-Fuqaha, Ala ;
Erbad, Aiman .
2021 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS), 2021,
[2]   Fine-Grained Data Selection for Improved Energy Efficiency of Federated Edge Learning [J].
Albaseer, Abdullatif ;
Abdallah, Mohamed ;
Al-Fuqaha, Ala ;
Erbad, Aiman .
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2022, 9 (05) :3258-3271
[3]  
[Anonymous], 2020, Cisco Annual Internet Report (2018-2023) White Paper
[4]  
Avriel M., 1976, Studies in Religion Series
[5]   Massive MIMO Systems With Non-Ideal Hardware: Energy Efficiency, Estimation, and Capacity Limits [J].
Bjornson, Emil ;
Hoydis, Jakob ;
Kountouris, Marios ;
Debbah, Merouane .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2014, 60 (11) :7112-7139
[6]  
Bodine-Baron E, 2011, LECT NOTES COMPUT SC, V6982, P117, DOI 10.1007/978-3-642-24829-0_12
[7]   Optimized Power Control Design for Over-the-Air Federated Edge Learning [J].
Cao, Xiaowen ;
Zhu, Guangxu ;
Xu, Jie ;
Wang, Zhiqin ;
Cui, Shuguang .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2022, 40 (01) :342-358
[8]   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
[9]   Dynamic Games for Social Model Training Service Market via Federated Learning Approach [J].
Cheng, Wenqing ;
Zou, Yuze ;
Xu, Jing ;
Liu, Wei .
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2022, 9 (01) :64-75
[10]   Federated Learning Over Wireless Networks: Convergence Analysis and Resource Allocation [J].
Dinh, Canh T. ;
Tran, Nguyen H. ;
Nguyen, Minh N. H. ;
Hong, Choong Seon ;
Bao, Wei ;
Zomaya, Albert Y. ;
Gramoli, Vincent .
IEEE-ACM TRANSACTIONS ON NETWORKING, 2021, 29 (01) :398-409