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
  • [11] FedBoost: Communication-Efficient Algorithms for Federated Learning
    Hamer, Jenny
    Mohri, Mehryar
    Suresh, Ananda Theertha
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [12] Ternary Compression for Communication-Efficient Federated Learning
    Xu, Jinjin
    Du, Wenli
    Jin, Yaochu
    He, Wangli
    Cheng, Ran
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (03) : 1162 - 1176
  • [13] Communication-efficient federated learning via knowledge distillation
    Wu, Chuhan
    Wu, Fangzhao
    Lyu, Lingjuan
    Huang, Yongfeng
    Xie, Xing
    NATURE COMMUNICATIONS, 2022, 13 (01)
  • [14] Federated Learning with Autotuned Communication-Efficient Secure Aggregation
    Bonawitz, Keith
    Salehi, Fariborz
    Konecny, Jakub
    McMahan, Brendan
    Gruteser, Marco
    CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, 2019, : 1222 - 1226
  • [15] On the Design of Communication-Efficient Federated Learning for Health Monitoring
    Chu, Dong
    Jaafar, Wael
    Yanikomeroglu, Halim
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 1128 - 1133
  • [16] Communication-Efficient Federated Learning For Massive MIMO Systems
    Mu, Yuchen
    Garg, Navneet
    Ratnarajah, Tharmalingam
    2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, : 578 - 583
  • [17] ALS Algorithm for Robust and Communication-Efficient Federated Learning
    Hurley, Neil
    Duriakova, Erika
    Geraci, James
    O'Reilly-Morgan, Diarmuid
    Tragos, Elias
    Smyth, Barry
    Lawlor, Aonghus
    PROCEEDINGS OF THE 2024 4TH WORKSHOP ON MACHINE LEARNING AND SYSTEMS, EUROMLSYS 2024, 2024, : 56 - 64
  • [18] 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
  • [19] Communication-Efficient Wireless Traffic Prediction with Federated Learning
    Gao, Fuwei
    Zhang, Chuanting
    Qiao, Jingping
    Li, Kaiqiang
    Cao, Yi
    MATHEMATICS, 2024, 12 (16)
  • [20] Communication-Efficient Design for Quantized Decentralized Federated Learning
    Chen, Li
    Liu, Wei
    Chen, Yunfei
    Wang, Weidong
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2024, 72 : 1175 - 1188