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
  • [1] Communication-Efficient Federated Learning with Adaptive Consensus ADMM
    He, Siyi
    Zheng, Jiali
    Feng, Minyu
    Chen, Yixin
    APPLIED SCIENCES-BASEL, 2023, 13 (09):
  • [2] Communication-Efficient and Federated Multi-Agent Reinforcement Learning
    Krouka, Mounssif
    Elgabli, Anis
    Ben Issaid, Chaouki
    Bennis, Mehdi
    IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2022, 8 (01) : 311 - 320
  • [3] Communication-efficient federated learning
    Chen, Mingzhe
    Shlezinger, Nir
    Poor, H. Vincent
    Eldar, Yonina C.
    Cui, Shuguang
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2021, 118 (17)
  • [4] Communication-Efficient Vertical Federated Learning
    Khan, Afsana
    ten Thij, Marijn
    Wilbik, Anna
    ALGORITHMS, 2022, 15 (08)
  • [5] Communication-Efficient Adaptive Federated Learning
    Wang, Yujia
    Lin, Lu
    Chen, Jinghui
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [6] FedQMIX: Communication-efficient federated learning via multi-agent reinforcement learning
    Cao, Shaohua
    Zhang, Hanqing
    Wen, Tian
    Zhao, Hongwei
    Zheng, Quancheng
    Zhang, Weishan
    Zheng, Danyang
    HIGH-CONFIDENCE COMPUTING, 2024, 4 (02):
  • [7] Communication-Efficient Federated Learning with Heterogeneous Devices
    Chen, Zhixiong
    Yi, Wenqiang
    Liu, Yuanwei
    Nallanathan, Arumugam
    ICC 2023-IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, 2023, : 3602 - 3607
  • [8] Communication-Efficient Federated Learning for Decision Trees
    Zhao, Shuo
    Zhu, Zikun
    Li, Xin
    Chen, Ying-Chi
    IEEE Transactions on Artificial Intelligence, 2024, 5 (11): : 5478 - 5492
  • [9] Communication-Efficient Federated Learning with Adaptive Quantization
    Mao, Yuzhu
    Zhao, Zihao
    Yan, Guangfeng
    Liu, Yang
    Lan, Tian
    Song, Linqi
    Ding, Wenbo
    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2022, 13 (04)
  • [10] Communication-Efficient Secure Aggregation for Federated Learning
    Ergun, Irem
    Sami, Hasin Us
    Guler, Basak
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 3881 - 3886