Latency Optimization for Blockchain-Empowered Federated Learning in Multi-Server Edge Computing

被引:14
|
作者
Nguyen, Dinh C. [1 ]
Hosseinalipour, Seyyedali [2 ]
Love, David J. [1 ]
Pathirana, Pubudu N. [3 ]
Brinton, Christopher G. [1 ]
机构
[1] Purdue Univ, Elmore Family Sch Elect & Comp Engn, W Lafayette, IN 47907 USA
[2] Univ Buffalo SUNY, Dept Elect Engn, Buffalo, NY 14228 USA
[3] Deakin Univ, Sch Engn, Waurn Ponds, Vic 3216, Australia
关键词
Federated learning; blockchain; edge computing; actor-critic learning; network optimization; RESOURCE-ALLOCATION; PRIVACY;
D O I
10.1109/JSAC.2022.3213344
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 new latency optimization problem for blockchain-based federated learning (BFL) in multi-server edge computing. In this system model, distributed mobile devices (MDs) communicate with a set of edge servers (ESs) to handle both machine learning (ML) model training and block mining simultaneously. To assist the ML model training for resource-constrained MDs, we develop an offloading strategy that enables MDs to transmit their data to one of the associated ESs. We then propose a new decentralized ML model aggregation solution at the edge layer based on a consensus mechanism to build a global ML model via peer-to-peer (P2P)-based blockchain communications. Blockchain builds trust among MDs and ESs to facilitate reliable ML model sharing and cooperative consensus formation, and enables rapid elimination of manipulated models caused by poisoning attacks. We formulate latency-aware BFL as an optimization aiming to minimize the system latency via joint consideration of the data offloading decisions, MDs' transmit power, channel bandwidth allocation for MDs' data offloading, MDs' computational allocation, and hash power allocation. Given the mixed action space of discrete offloading and continuous allocation variables, we propose a novel deep reinforcement learning scheme with a parameterized advantage actor critic algorithm. We theoretically characterize the convergence properties of BFL in terms of the aggregation delay, mini-batch size, and number of P2P communication rounds. Our numerical evaluation demonstrates the superiority of our proposed scheme over baselines in terms of model training efficiency, convergence rate, system latency, and robustness against model poisoning attacks.
引用
收藏
页码:3373 / 3390
页数:18
相关论文
共 50 条
  • [1] Lightweight Blockchain-Empowered Secure and Efficient Federated Edge Learning
    Jin, Rui
    Hu, Jia
    Min, Geyong
    Mills, Jed
    [J]. IEEE TRANSACTIONS ON COMPUTERS, 2023, 72 (11) : 3314 - 3325
  • [2] Optimizing Task Assignment for Reliable Blockchain-Empowered Federated Edge Learning
    Kang, Jiawen
    Xiong, Zehui
    Li, Xuandi
    Zhang, Yang
    Niyato, Dusit
    Leung, Cyril
    Miao, Chunyan
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (02) : 1910 - 1923
  • [3] Blockchain-empowered Federated Learning: Challenges, Solutions, and Future Directions
    Zhu, Juncen
    Cao, Jiannong
    Saxena, Divya
    Jiang, Shan
    Ferradi, Houda
    [J]. ACM COMPUTING SURVEYS, 2023, 55 (11)
  • [4] Blockchain-Empowered Secure Aerial Edge Computing for AIoT Devices
    Zhang, Zufan
    Zeng, Kewen
    Yi, Yinxue
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (01): : 84 - 94
  • [5] Blockchain-empowered secure federated learning system: Architecture and applications
    Yu, Feng
    Lin, Hui
    Wang, Xiaoding
    Yassine, Abdussalam
    Hossain, M. Shamim
    [J]. COMPUTER COMMUNICATIONS, 2022, 196 : 55 - 65
  • [6] Blockchain-Empowered Federated Learning Through Model and Feature Calibration
    Wang, Qianlong
    Liao, Weixian
    Guo, Yifan
    Mcguire, Michael
    Yu, Wei
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (04): : 5770 - 5780
  • [7] Cooperative Federated Learning and Model Update Verification in Blockchain-Empowered Digital Twin Edge Networks
    Jiang, Li
    Zheng, Hao
    Tian, Hui
    Xie, Shengli
    Zhang, Yan
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (13) : 11154 - 11167
  • [8] Blockchain-Empowered Distributed Multicamera Multitarget Tracking in Edge Computing
    Wang, Shuai
    Sheng, Hao
    Zhang, Yang
    Yang, Da
    Shen, Jiahao
    Chen, Rongshan
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2024, 20 (01) : 369 - 379
  • [9] Online Deep Reinforcement Learning for Computation Offloading in Blockchain-Empowered Mobile Edge Computing
    Qiu, Xiaoyu
    Liu, Luobin
    Chen, Wuhui
    Hong, Zicong
    Zheng, Zibin
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2019, 68 (08) : 8050 - 8062
  • [10] BFLMeta: Blockchain-Empowered Metaverse with Byzantine-Robust Federated Learning
    Vu Tuan Truong
    Hoang, Duc N. M.
    Long Bao Le
    [J]. IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 5537 - 5542