A Hierarchical Incentive Mechanism for Federated Learning

被引:1
|
作者
Huang, Jiwei [1 ]
Ma, Bowen [1 ]
Wu, Yuan [2 ,3 ]
Chen, Ying [4 ]
Shen, Xuemin [5 ]
机构
[1] China Univ Petr, Beijing Key Lab Petr Data Min, Beijing 102249, Peoples R China
[2] Univ Macau, State Key Lab Internet Things Smart City, Macau 999078, Peoples R China
[3] Univ Macau, Dept Comp & Informat Sci, Macau 999078, Peoples R China
[4] Beijing Informat Sci & Technol Univ, Comp Sch, Beijing 100101, Peoples R China
[5] Univ Waterloo, Dept Elect & Comp Engn, Waterloo, ON N2L 3G1, Canada
基金
北京市自然科学基金;
关键词
Games; Contracts; Training; Data models; Task analysis; Computational modeling; Sensors; Incentive mechanism; federated learning; contract theory; Stackelberg game; RESOURCE-ALLOCATION; CONTRACT DESIGN; OPTIMIZATION; NETWORKS;
D O I
10.1109/TMC.2024.3423399
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the explosive development of mobile computing, federated learning (FL) has been considered as a promising distributed training framework for addressing the shortage of conventional cloud based centralized training. In FL, local model owners (LMOs) individually train their respective local models and then upload the trained local models to the task publisher (TP) for aggregation to obtain the global model. When the data provided by LMOs do not meet the requirements for model training, they can recruit workers to collect data. In this paper, by considering the interactions among the TP, LMOs and workers, we propose a three-layer hierarchical game framework. However, there are two challenges. First, information asymmetry between workers and LMOs may result in that the workers hide their types. Second, incentive mismatch between TP and LMOs may result in a lack of LMOs' willingness to participate in FL. Therefore, we decompose the hierarchical-based framework into two layers to address these challenges. For the lower-layer, we leverage the contract theory to ensure truthful reporting of the workers' types, based on which we simplify the feasible conditions of the contract and design the optimal contract. For the upper-layer, the Stackelberg game is adopted to model the interactions between the TP and LMOs, and we derive the Nash equilibrium and Stackelberg equilibrium solutions. Moreover, we develop an iterative Hierarchical-based Utility Maximization Algorithm (HUMA) to solve the coupling problem between upper-layer and lower-layer games. Extensive numerical experimental results verify the effectiveness of HUMA, and the comparison results illustrate the performance gain of HUMA.
引用
收藏
页码:12731 / 12747
页数:17
相关论文
共 50 条
  • [41] InFEDge: A Blockchain-Based Incentive Mechanism in Hierarchical Federated Learning for End-Edge-Cloud Communications
    Wang, Xiaofei
    Zhao, Yunfeng
    Qiu, Chao
    Liu, Zhicheng
    Nie, Jiangtian
    Leung, Victor C. M.
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2022, 40 (12) : 3325 - 3342
  • [42] Incentive-driven long-term optimization for hierarchical federated learning
    Su, Lina
    Li, Zongpeng
    COMPUTER NETWORKS, 2023, 234
  • [43] An Incentive Mechanism for Long-Term Federated Learning in Autonomous Driving
    Fu, Yuchuan
    Li, Zhenyu
    Liu, Sha
    Li, Changle
    Yu, F. Richard
    Cheng, Nan
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (09): : 15642 - 15655
  • [44] Incentive Mechanism of Blockchain-Based Reverse Auction for Federated Learning
    Cui, Bo
    Dang, Li
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 1043 - 1048
  • [45] Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation
    Luo, Bing
    Feng, Yutong
    Wang, Shiqiang
    Huang, Jianwei
    Tassiulas, Leandros
    2023 IEEE 43RD INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, ICDCS, 2023, : 545 - 555
  • [46] A Secure and Fair Federated Learning Framework Based on Consensus Incentive Mechanism
    Zhu, Feng
    Hu, Feng
    Zhao, Yanchao
    Chen, Bing
    Tan, Xiaoyang
    MATHEMATICS, 2024, 12 (19)
  • [47] An incentive mechanism for horizontal federated learning based on principle of compound interest
    Guo, Jingjing
    Xiong, Liangcheng
    Li, Jiaxing
    Liu, Jiuzun
    Tian, Siyi
    Li, Haiyang
    PHYSICAL COMMUNICATION, 2023, 60
  • [48] Contract Theory Based Incentive Mechanism for Clustered Vehicular Federated Learning
    Wang, Siyang
    Zhao, Haitao
    Wen, Wanli
    Xia, Wenchao
    Wang, Bin
    Zhu, Hongbo
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (07) : 8134 - 8147
  • [49] CSRA: Robust Incentive Mechanism Design for Differentially Private Federated Learning
    Yang, Yunchao
    Hu, Miao
    Zhou, Yipeng
    Liu, Xuezheng
    Wu, Di
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 892 - 906
  • [50] Incentive Mechanism for Horizontal Federated Learning Based on Reputation and Reverse Auction
    Zhang, Jingwen
    Wu, Yuezhou
    Pan, Rong
    PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021), 2021, : 947 - 956