Cluster-Based Cooperative Digital Over-the-Air Aggregation for Wireless Federated Edge Learning

被引:0
|
作者
Jiang, Ruichen [1 ]
Zhou, Sheng [1 ]
机构
[1] Tsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol, Dept Elect Engn, Beijing 100084, Peoples R China
来源
2020 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA (ICCC) | 2020年
基金
国家重点研发计划;
关键词
D O I
10.1109/iccc49849.2020.9238982
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, we study a federated learning system at the wireless edge that uses over-the-air computation (AirComp). In such a system, users transmit their messages over a multi-access channel concurrently to achieve fast model aggregation. Recently, an AirComp scheme based on digital modulation has been proposed featuring one-bit gradient quantization and truncated channel inversion at users and a majority-voting based decoder at the fusion center (FC). We propose an improved digital AirComp scheme to relax its requirements on the transmitters, where users perform phase correction and transmit with full power. To characterize the decoding failure probability at the FC, we introduce the normalized detection signal-to-noise ratio (SNR), which can be interpreted as the effective participation rate of users. To mitigate wireless fading, we further propose a cluster-based system and design the relay selection scheme based on the normalized detection SNR. By local data fusion within each cluster and relay selection, our scheme can fully exploit spatial diversity to increase the effective number of voting users and accelerate model convergence.
引用
收藏
页码:887 / 892
页数:6
相关论文
共 50 条
  • [1] Broadband Digital Over-the-Air Computation for Wireless Federated Edge Learning
    You, Lizhao
    Zhao, Xinbo
    Cao, Rui
    Shao, Yulin
    Fu, Liqun
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (05) : 5212 - 5228
  • [2] Over-the-Air Aggregation-Based Federated Learning in Cache-Enabled Wireless Edge Networks
    Hong, Jun-Pyo
    Park, Sangjun
    Choi, Wan
    ICC 2023-IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, 2023, : 1994 - 1999
  • [3] Broadband Digital Over-the-Air Computation for Asynchronous Federated Edge Learning
    Zhao, Xinbo
    You, Lizhao
    Rui Cao
    Shao, Yulin
    Fu, Liqun
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 5359 - 5364
  • [4] Hierarchical Over-the-Air Federated Edge Learning
    Aygun, Ozan
    Kazemi, Mohammad
    Gunduz, Deniz
    Duman, Tolga M.
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 3376 - 3381
  • [5] An Overview on Over-the-Air Federated Edge Learning
    Cao, Xiaowen
    Lyu, Zhonghao
    Zhu, Guangxu
    Xu, Jie
    Xu, Lexi
    Cui, Shuguang
    IEEE WIRELESS COMMUNICATIONS, 2024, 31 (03) : 202 - 210
  • [6] Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning
    Zhang, Chong
    Dong, Min
    Liang, Ben
    Afanat, Ali
    Ahmed, Yahia
    2024 IEEE 25TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS, SPAWC 2024, 2024, : 36 - 40
  • [7] Over-the-Air Federated Learning via Weighted Aggregation
    Azimi-Abarghouyi, Seyed Mohammad
    Tassiulas, Leandros
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (12) : 18240 - 18253
  • [8] Federated Edge Learning With Misaligned Over-the-Air Computation
    Shao, Yulin
    Gunduz, Deniz
    Liew, Soung Chang
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (06) : 3951 - 3964
  • [9] Over-the-Air Federated Edge Learning With Hierarchical Clustering
    Aygun, Ozan
    Kazemi, Mohammad
    Gunduz, Deniz
    Duman, Tolga M.
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (12) : 17856 - 17871
  • [10] Federated Edge Learning with Misaligned Over-The-Air Computation
    Shao, Yulin
    Gunduz, Deniz
    Liew, Soung Chang
    SPAWC 2021: 2021 IEEE 22ND INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (IEEE SPAWC 2021), 2021, : 236 - 240