Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

被引:2
|
作者
Xu, Xing [1 ]
Li, Rongpeng [1 ]
Zhao, Zhifeng [2 ]
Zhang, Honggang [1 ]
机构
[1] Zhejiang Univ, Hangzhou, Peoples R China
[2] Zhejiang Lab, Hangzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
Independent Reinforcement Learning; Federated Learning; Consensus Algorithm; Communication Overheads; Utility Function;
D O I
10.1109/ICC45855.2022.9838936
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
The paper considers independent reinforcement learning (IRL) for multi-agent decision-making process in the paradigm of federated learning (FL). We show that FL can clearly improve the policy performance of IRL in terms of training efficiency and stability. However, since the policy parameters are trained locally and aggregated iteratively through a central server in FL, frequent information exchange incurs a large amount of communication overheads. To reach a good balance between improving the model's convergence performance and reducing the required communication and computation overheads, this paper proposes a system utility function and develops a consensus-based optimization scheme on top of the periodic averaging method, which introduces the consensus algorithm into FL for the exchange of a model's local gradients. This paper also provides novel convergence guarantees for the developed method, and demonstrates its superior effectiveness and efficiency in improving the system utility value through theoretical analyses and numerical simulation results.
引用
收藏
页码:80 / 85
页数:6
相关论文
共 50 条
  • [31] Communication-Efficient Generalized Neuron Matching for Federated Learning
    Hu, Sixu
    Li, Qinbin
    He, Bingsheng
    PROCEEDINGS OF THE 52ND INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, ICPP 2023, 2023, : 254 - 263
  • [32] Communication-efficient federated learning with stagewise training strategy
    Cheng, Yifei
    Shen, Shuheng
    Liang, Xianfeng
    Liu, Jingchang
    Chen, Joya
    Zhang, Tie
    Chen, Enhong
    NEURAL NETWORKS, 2023, 167 : 460 - 472
  • [33] Communication-efficient and Scalable Decentralized Federated Edge Learning
    Yapp, Austine Zong Han
    Koh, Hong Soo Nicholas
    Lai, Yan Ting
    Kang, Jiawen
    Li, Xuandi
    Ng, Jer Shyuan
    Jiang, Hongchao
    Lim, Wei Yang Bryan
    Xiong, Zehui
    Niyato, Dusit
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 5032 - 5035
  • [34] Communication-Efficient Federated Learning with Adaptive Parameter Freezing
    Chen, Chen
    Xu, Hong
    Wang, Wei
    Li, Baochun
    Li, Bo
    Chen, Li
    Zhang, Gong
    2021 IEEE 41ST INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2021), 2021, : 1 - 11
  • [35] FedCS: Communication-Efficient Federated Learning with Compressive Sensing
    Liu, Ye
    Chang, Shan
    Liu, Yiqi
    2022 IEEE 28TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, ICPADS, 2022, : 17 - 24
  • [36] Communication-Efficient and Personalized Federated Lottery Ticket Learning
    Seo, Sejin
    Ko, Seung-Woo
    Park, Jihong
    Kim, Seong-Lyun
    Bennis, Mehdi
    SPAWC 2021: 2021 IEEE 22ND INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (IEEE SPAWC 2021), 2020, : 581 - 585
  • [37] Communication-Efficient Federated Learning for Large-Scale Multiagent Systems in ISAC: Data Augmentation With Reinforcement Learning
    Ouyang, Wenjiang
    Liu, Qian
    Mu, Junsheng
    AI-Dulaimi, Anwer
    Jing, Xiaojun
    Liu, Qilie
    IEEE SYSTEMS JOURNAL, 2024, : 1893 - 1904
  • [38] Communication-efficient federated learning via personalized filter pruning
    Min, Qi
    Luo, Fei
    Dong, Wenbo
    Gu, Chunhua
    Ding, Weichao
    INFORMATION SCIENCES, 2024, 678
  • [39] Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
    Ji, Shaoxiong
    Jiang, Wenqi
    Walid, Anwar
    Li, Xue
    IEEE INTELLIGENT SYSTEMS, 2022, 37 (02) : 27 - 34
  • [40] Communication-Efficient Federated Learning Algorithm Based on Event Triggering
    Gao H.
    Yang L.
    Zhu J.
    Zhang M.
    Wu Q.
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2023, 45 (10): : 3710 - 3718