Accelerating convergence in wireless federated learning by sharing marginal data

被引:0
|
作者
Seo, Eunil [1 ]
Pham, Vinh [2 ]
Elmroth, Erik [1 ]
机构
[1] Umea Univ, Dept Comp Sci, Umea, Sweden
[2] Sungkyunkwan Univ, Comp Sci & Engn Dept, Suwon 16419, South Korea
来源
2023 INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING, ICOIN | 2023年
关键词
Edge computing; federated learning; data sharing; wireless mobile network;
D O I
10.1109/ICOIN56518.2023.10048937
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Deploying federated learning (FL) over wireless mobile networks can be expensive because of the cost of wireless communication resources. Efforts have been made to reduce communication costs by accelerating model convergence, leading to the development of model-driven methods based on feature extraction, model-integrated algorithms, and client selection. However, the resulting performance gains are limited by the dependence of neural network convergence on input data quality. This work, therefore, investigates the use of marginal shared data (e.g., a single data entry) to accelerate model convergence and thereby reduce communication costs in FL. Experimental results show that sharing even a single piece of data can improve performance by 14.6% and reduce communication costs by 61.13% when using the federated averaging algorithm (FedAvg). Marginal data sharing could therefore be an attractive and practical solution in privacy-flexible environments or collaborative operational systems such as fog robotics and vehicles. Moreover, by assigning new labels to the shared data, it is possible to extend the number of classifying labels of an FL model even when the initial input datasets lack the labels in question.
引用
收藏
页码:122 / 127
页数:6
相关论文
共 50 条
  • [41] Explainable federated learning scheme for secure healthcare data sharing
    Zhao, Liutao
    Xie, Haoran
    Zhong, Lin
    Wang, Yujue
    HEALTH INFORMATION SCIENCE AND SYSTEMS, 2024, 12 (01):
  • [42] MadFed: Enhancing Federated Learning With Marginal-Data Model Fusion
    Seo, Eunil
    Elmroth, Erik
    IEEE ACCESS, 2023, 11 : 102669 - 102680
  • [43] Learning Efficiency Maximization for Wireless Federated Learning With Heterogeneous Data and Clients
    Ouyang, Jinhao
    Liu, Yuan
    IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2024, 10 (06) : 2282 - 2295
  • [44] On the Convergence Time of Federated Learning Over Wireless Networks Under Imperfect CSI
    Pase, Francesco
    Giordani, Marco
    Zorzi, Michele
    2021 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS), 2021,
  • [45] Joint Optimization of Convergence and Latency for Hierarchical Federated Learning Over Wireless Networks
    Sun, Haofeng
    Tian, Hui
    Zheng, Jingheng
    Ni, Wanli
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2024, 13 (03) : 691 - 695
  • [46] Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data
    Ahn, Jin-Hyun
    Simeone, Osvaldo
    Kang, Joonhyuk
    2019 IEEE 30TH ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS (PIMRC), 2019, : 1138 - 1143
  • [47] Federated Learning With Non-IID Data in Wireless Networks
    Zhao, Zhongyuan
    Feng, Chenyuan
    Hong, Wei
    Jiang, Jiamo
    Jia, Chao
    Quek, Tony Q. S.
    Peng, Mugen
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (03) : 1927 - 1942
  • [48] ESync: Accelerating Intra-Domain Federated Learning in Heterogeneous Data Centers
    Li, Zonghang
    Zhou, Huaman
    Zhou, Tianyao
    Yu, Hongfang
    Xu, Zenglin
    Sun, Gang
    IEEE TRANSACTIONS ON SERVICES COMPUTING, 2022, 15 (04) : 2261 - 2274
  • [49] Client Selection for Wireless Federated Learning With Data and Latency Heterogeneity
    Chen, Xiaobing
    Zhou, Xiangwei
    Zhang, Hongchao
    Sun, Mingxuan
    Vincent Poor, H.
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (19): : 32183 - 32196
  • [50] DSFL: a blockchain-based data sharing and federated learning framework
    Niu, Haiqian
    Zhang, Xing
    Chu, Zhiguang
    Shi, Wei
    APPLIED INTELLIGENCE, 2025, 55 (06)