Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

被引:3
|
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
  • [21] Communication-Efficient Robust Federated Learning with Noisy Labels
    Li, Junyi
    Pei, Jian
    Huang, Heng
    PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, : 914 - 924
  • [22] Communication-Efficient Federated Learning With Data and Client Heterogeneity
    Zakerinia, Hossein
    Talaei, Shayan
    Nadiradze, Giorgi
    Alistarh, Dan
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
  • [23] Communication-Efficient Federated Learning via Predictive Coding
    Yue, Kai
    Jin, Richeng
    Wong, Chau-Wai
    Dai, Huaiyu
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2022, 16 (03) : 369 - 380
  • [24] Communication-Efficient Wireless Traffic Prediction with Federated Learning
    Gao, Fuwei
    Zhang, Chuanting
    Qiao, Jingping
    Li, Kaiqiang
    Cao, Yi
    MATHEMATICS, 2024, 12 (16)
  • [25] Communication-Efficient Federated Learning With Binary Neural Networks
    Yang, Yuzhi
    Zhang, Zhaoyang
    Yang, Qianqian
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2021, 39 (12) : 3836 - 3850
  • [26] Communication-efficient Federated Learning with Cooperative Filter Selection
    Yang, Zhao
    Sun, Qingshuang
    2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 2172 - 2176
  • [27] Communication-Efficient Federated Learning With Gradual Layer Freezing
    Malan, Erich
    Peluso, Valentino
    Calimera, Andrea
    Macii, Enrico
    IEEE EMBEDDED SYSTEMS LETTERS, 2023, 15 (01) : 25 - 28
  • [28] Communication-Efficient Federated Learning Based on Compressed Sensing
    Li, Chengxi
    Li, Gang
    Varshney, Pramod K.
    IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (20) : 15531 - 15541
  • [29] On the Convergence of Communication-Efficient Local SGD for Federated Learning
    Gao, Hongchang
    Xu, An
    Huang, Heng
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 7510 - 7518
  • [30] A Cooperative Analysis to Incentivize Communication-Efficient Federated Learning
    Li, Youqi
    Li, Fan
    Yang, Song
    Zhang, Chuan
    Zhu, Liehuang
    Wang, Yu
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (10) : 10175 - 10190