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 50 条
  • [41] Cost-Efficient Shuffling and Regrouping Based Defense for Federated Learning
    Huang, Shu-Meng
    Chen, Yu-Wen
    Kuo, Jian-Jhih
    2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
  • [42] Cost-Efficient Resource Allocation Method for Heterogeneous Cloud Environments
    Szabo, Marton
    Hajay, David
    Szalayz, Mark
    INFOCOMMUNICATIONS JOURNAL, 2018, 10 (01): : 15 - 21
  • [43] Cost-efficient resource allocation method for heterogeneous cloud environments
    2018, Scientific Association for Infocommunications (10):
  • [44] Towards Efficient Federated Learning via Vehicle Selection and Resource Optimization in IoV
    Gong, Nan
    Yan, Guozhi
    Zhang, Hao
    Xiao, Ke
    Yang, Zuoxiu
    Li, Chuzhao
    Liu, Kai
    NEURAL COMPUTING FOR ADVANCED APPLICATIONS, NCAA 2024, PT II, 2025, 2182 : 117 - 131
  • [45] Joint Client Selection and Training Optimization for Energy-Efficient Federated Learning
    Yan, Kang
    Shu, Nina
    Wu, Tao
    Liu, Chunsheng
    Huang, Jun
    Yu, Jingbo
    2023 19TH INTERNATIONAL CONFERENCE ON MOBILITY, SENSING AND NETWORKING, MSN 2023, 2023, : 849 - 854
  • [46] Data-Driven Participant Selection and Bandwidth Allocation for Heterogeneous Federated Edge Learning
    Albaseer, Abdullatif
    Abdallah, Mohamed
    Al-Fuqaha, Ala
    Erbad, Aiman
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2023, 53 (09): : 5848 - 5860
  • [47] Joint Selection of Local Trainers and Resource Allocation for Federated Learning in Open RAN Intelligent Controllers
    Singh, Amardip Kumar
    Nguyen, Kim Khoa
    2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, : 1874 - 1879
  • [48] Joint Model Pruning and Device Selection for Communication-Efficient Federated Edge Learning
    Liu, Shengli
    Yu, Guanding
    Yin, Rui
    Yuan, Jiantao
    Shen, Lei
    Liu, Chonghe
    IEEE TRANSACTIONS ON COMMUNICATIONS, 2022, 70 (01) : 231 - 244
  • [49] Energy-efficient client selection in federated learning with heterogeneous data on edge
    Jianxin Zhao
    Yanhao Feng
    Xinyu Chang
    Chi Harold Liu
    Peer-to-Peer Networking and Applications, 2022, 15 : 1139 - 1151
  • [50] Energy-efficient client selection in federated learning with heterogeneous data on edge
    Zhao, Jianxin
    Feng, Yanhao
    Chang, Xinyu
    Liu, Chi Harold
    PEER-TO-PEER NETWORKING AND APPLICATIONS, 2022, 15 (02) : 1139 - 1151