A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 11 Issue 1
Jan.  2024

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 15.3, Top 1 (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2024  >  11(1): 88-102
C. Tang, B. Yang, X. Xie, G. R. Chen, M. Al-qaness, and Y. Liu, “An incentive mechanism for federated learning: A continuous zero-determinant strategy approach,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 88–102, Jan. 2024. doi: 10.1109/JAS.2023.123828
Citation: C. Tang, B. Yang, X. Xie, G. R. Chen, M. Al-qaness, and Y. Liu, “An incentive mechanism for federated learning: A continuous zero-determinant strategy approach,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 88–102, Jan. 2024. doi: 10.1109/JAS.2023.123828
shu

An Incentive Mechanism for Federated Learning: A Continuous Zero-Determinant Strategy Approach

doi: 10.1109/JAS.2023.123828
Funds:  This work was partially supported by the National Natural Science Foundation of China (62173308), the Natural Science Foundation of Zhejiang Province of China (LR20F030001), and the Jinhua Science and Technology Project (2022-1-042)
More Information
    Abstract
  • As a representative emerging machine learning technique, federated learning (FL) has gained considerable popularity for its special feature of “making data available but not visible”. However, potential problems remain, including privacy breaches, imbalances in payment, and inequitable distribution. These shortcomings let devices reluctantly contribute relevant data to, or even refuse to participate in FL. Therefore, in the application of FL, an important but also challenging issue is to motivate as many participants as possible to provide high-quality data to FL. In this paper, we propose an incentive mechanism for FL based on the continuous zero-determinant (CZD) strategies from the perspective of game theory. We first model the interaction between the server and the devices during the FL process as a continuous iterative game. We then apply the CZD strategies for two players and then multiple players to optimize the social welfare of FL, for which we prove that the server can keep social welfare at a high and stable level. Subsequently, we design an incentive mechanism based on the CZD strategies to attract devices to contribute all of their high-accuracy data to FL. Finally, we perform simulations to demonstrate that our proposed CZD-based incentive mechanism can indeed generate high and stable social welfare in FL.

     

    • FullText(HTML)
  • loading
    • References(46)
  • [1]
    K. Letaief, W. Chen, Y. Shi, J. Zhang, and Y. Zhang, “The roadmap to 6G: AI empowered wireless networks,” IEEE Commun. Mag., vol. 57, no. 8, pp. 84–90, Aug. 2019. doi: 10.1109/MCOM.2019.1900271
    [2]
    C. Zhou, H. Tao, Y. Chen, V. Stojanovic, and W. Paszke, “Robust point-to-point iterative learning control for constrained systems: A minimum energy approach,” Int. J. Robust Nonlinear Control, vol. 32, no. 18, pp. 10139–10161, Sept. 2022. doi: 10.1002/rnc.6354
    [3]
    H. Tao, J. Qiu, Y. Chen, V. Stojanovic, and L. Cheng, “Unsupervised cross-domain rolling bearing fault diagnosis based on time-frequency information fusion,” J. Frankl. Inst., vol. 360, no. 2, pp. 1454–1477, Jan. 2023. doi: 10.1016/j.jfranklin.2022.11.004
    [4]
    Z. Zhuang, H. Tao, Y. Chen, V. Stojanovic, and W. Paszke, “An optimal iterative learning control approach for linear systems with nonuniform trial lengths under input constraints,” IEEE Trans. Syst. Man Cybern. Syst., vol. 53, no. 6, pp. 3461–3473, Jun. 2023. doi: 10.1109/TSMC.2022.3225381
    [5]
    N. Aitzhan and D. Svetinovic, “Security and privacy in decentralized energy trading through multi-signatures, blockchain and anonymous messaging streams,” IEEE Trans. Dependable Secure Comput., vol. 15, no. 5, pp. 840–852, Sep.–Oct. 2018. doi: 10.1109/TDSC.2016.2616861
    [6]
    L. Liu, J. Zhang, S. Song, and K. Letaief, “Client-edge-cloud hierarchical federated learning,” in Proc. IEEE Int. Conf. Commun., Dublin, Ireland, 2020, pp. 1–6.
    [7]
    Q. Yang, Y. Liu, Y. Cheng, Y. Kang, T. Chen, and H. Yu, “Federated learning,” Synth. Lect. Artif. Intell. Mach. Learn., vol. 13, no. 3, pp. 1–207, Dec. 2019.
    [8]
    A. Hard, K. Rao, R. Mathews, S. Ramaswamy, F. Beaufays, S. Augenstein, H. Eichner, C. Kiddon, and D. Ramage, “Federated learning for mobile keyboard prediction,” 2018, [Online]. Available: https https://arxiv.org/abs/1811.03604.
    [9]
    Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated machine learning: conceptand applications,” ACM Trans. Intell. Syst. Technol., vol. 10, no. 2, pp. 1–19, Jan. 2019.
    [10]
    L. Khan, S. Pandey, N. Tran, W. Saad, Z. Han, M. Nguyen, and C. Hong, “Federated learning for edge networks: Resource optimization and incentive mechanism,” IEEE Commun. Mag., vol. 58, no. 10, pp. 88–93, Oct. 2020. doi: 10.1109/MCOM.001.1900649
    [11]
    W. Lim, J. Huang, Z. Xiong, J. Kang, D. Niyato, X. Hua, C. Leung, and C. Miao, “Towards federated learning in uavenabled internet of vehicles: A multi-dimensional contractmatching approach,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 8, pp. 5140–5154, Aug. 2021. doi: 10.1109/TITS.2021.3056341
    [12]
    N. Ding, Z. Fang, and J. Huang, “Optimal contract design for efficient federated learning with multi-dimensional private information,” IEEE J. Sel. Areas. Commun., vol. 39, no. 1, pp. 186–200, Jan. 2021. doi: 10.1109/JSAC.2020.3036944
    [13]
    N. Tran, W. Bao, A. Zomaya, M. Nguyen, and C. Hong, “Federated learning over wireless networks: Optimization model design and analysis,” in Proc. IEEE INFOCOM, Paris, France, 2019, pp. 1387–1395.
    [14]
    Y. Liu, X. Yuan, Z. Xiong, J. Kang, X. Wang, and D. Niyato, “Federated learning for 6G communications: Challenges, methods, and future directions,” China Commun., vol. 17, no. 9, pp. 105–118, Sept. 2020. doi: 10.23919/JCC.2020.09.009
    [15]
    H. Yu, Z. Liu, Y. Liu, T. Chen, M. Cong, X. Weng, D. Niyato, and Q. Yang, “A fairness-aware incentive scheme for federated learning,” in Proc. AAAI/ACM Conf. AI, Ethics, and Society, pp. 393–399, Feb. 2020.
    [16]
    X. Wang, C. Wang, X. Li, V. Leung, and T. Taleb, “Federated deep reinforcement learning for internet of things with decentralized cooperative edge caching,” IEEE Internet Things J., vol. 7, no. 10, pp. 9441–9455, Oct. 2020. doi: 10.1109/JIOT.2020.2986803
    [17]
    L. Xue, C. Sun, D. Wunsch, Y. Zhou, and F. Yu, “An adaptive strategy via reinforcement learning for the prisoner’s dilemma game,” IEEE/CAA J. Autom. Sinica, vol. 5, no. 1, pp. 301–310, Jan. 2018. doi: 10.1109/JAS.2017.7510466
    [18]
    J. Wang, Y. Hong, J. Wang, J. Xu, Y. Tang, Q. Han, and J. Kurths, “Cooperative and competitive multi-agent systems: From optimization to games,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 5, pp. 763–783, May 2022. doi: 10.1109/JAS.2022.105506
    [19]
    P. Y. Zhang, M. C. Zhou, C. X. Li, and A. Abusorrah, “Dynamic evolutionary game-based modeling, analysis and performance enhancement of blockchain channels,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 1, pp. 188–202, Jan. 2023. doi: 10.1109/JAS.2022.105911
    [20]
    J. Kang, Z. Xiong, D. Niyato, S. Xie, and J. Zhang, “Incentive mechanism for reliable federated learning: A joint optimization approach to combining reputation and contract theory,” IEEE Internet Things J., vol. 6, no. 6, pp. 10700–10714, Dec. 2019. doi: 10.1109/JIOT.2019.2940820
    [21]
    W. Lim, Z. Xiong, C. Miao, D. Niyato, Q. Yang, C. Leung, and H. Poor, “Hierarchical incentive mechanism design for federated machine learning in mobile networks,” IEEE Internet Things J., vol. 7, no. 10, pp. 9575–9588, Oct. 2020. doi: 10.1109/JIOT.2020.2985694
    [22]
    S. Pandey, N. Tran, M. Bennis, Y. Tun, A. Manzoor, and C. Hong, “A crowdsourcing framework for on-device federated learning,” IEEE Trans. Wirel. Commun., vol. 19, no. 5, pp. 3241–3256, May 2020. doi: 10.1109/TWC.2020.2971981
    [23]
    T. Thi Le, N. Tran, Y. Tun, M. Nguyen, S. Pandey, Z. Han, and C. Hong, “An incentive mechanism for federated learning in wireless cellular networks: An auction approach,” IEEE Trans. Wirel. Commun., vol. 20, no. 8, pp. 4874–4887, Aug. 2021. doi: 10.1109/TWC.2021.3062708
    [24]
    S. Fan, H. Zhang, Z. Wang, and W. Cai, “Mobile devices strategies in blockchain-based federated learning: A dynamic game perspective,” IEEE Trans. Netw. Sci. Eng., vol. 10, no. 3, pp. 1376–1388, May-Jun. 2023. doi: 10.1109/TNSE.2022.3163791
    [25]
    Q. Zhang, J. Zhu, S. Gao, Z. Xiong, Q. Ding, and G. Piao, “Incentive mechanism for federated learning based on blockchain and Bayesian game,” Sci. Sin. Inform., vol. 52, no. 6, pp. 971–991, Jun. 2022. doi: 10.1360/SSI-2022-0020
    [26]
    Z. Su, Y. Wang, T. Luan, N. Zhang, F. Li, T. Chen, and H. Cao, “Secure and efficient federated learning for smart grid with edge-cloud collaboration,” IEEE Trans. Industr. Inform., vol. 18, no. 2, pp. 1333–1344, Feb. 2022. doi: 10.1109/TII.2021.3095506
    [27]
    Y. Jiao, P. Wang, D. Niyato, B. Lin, and D. Kim, “Toward an automated auction framework for wireless federated learning services market,” IEEE Trans. Mob. Comput., vol. 20, no. 10, pp. 3034–3048, Oct. 2021. doi: 10.1109/TMC.2020.2994639
    [28]
    Y. Zhan, P. Li, Z. Qu, D. Zeng, and S. Guo, “A learning-based incentive mechanism for federated learning,” IEEE Internet Things J., vol. 7, no. 7, pp. 6360–6368, Jul. 2020. doi: 10.1109/JIOT.2020.2967772
    [29]
    Y. Zhan and J. Zhang, “An incentive mechanism design for efficient edge learning by deep reinforcement learning approach,” in Proc. IEEE INFOCOM, Toronto, Canada, 2020, pp. 2489–2498.
    [30]
    W. Press and F. Dyson, “Iterated prisoner’s dilemma contains strategies that dominate any evolutionary opponent,” Proc. Nat. Acad. Sci. USA, vol. 109, no. 26, pp. 10409–10413, May 2012. doi: 10.1073/pnas.1206569109
    [31]
    C. Hilbe, B. Wu, A. Traulsen, and M. Nowak, “Cooperation and control in multiplayer social dilemmas,” Proc. Nat. Acad. Sci. USA, vol. 111, no. 46, pp. 16425–16430, Oct. 2014. doi: 10.1073/pnas.1407887111
    [32]
    H. Zhang, D. Niyato, L. Song, T. Jiang, and Z. Han, “Zero-determinant strategy for resource sharing in wireless cooperations,” IEEE Trans. Wirel. Commun., vol. 15, no. 3, pp. 2179–2192, Mar. 2016. doi: 10.1109/TWC.2015.2499185
    [33]
    M. Wu and C. Tang, “Price of fairness for zero-determinant strategies in iterated prisoner’s dilemma,” in Proc. IEEE Chinese Control Conf., Shanghai, China, 2021, pp. 770–775.
    [34]
    R. Tan, Q. Su, B. Wu, and L. Wang, “Payoff control in repeated games,” in Proc. IEEE Chin. Control Decis. Conf., Kunming, China, 2021, pp. 997–1005.
    [35]
    C. Tang, C. Li, X. Yu, Z. Zheng, and Z. Chen, “Cooperative mining in blockchain networks with zero-determinant strategies,” IEEE Trans. Cybern., vol. 50, no. 10, pp. 4544–4549, Oct. 2020. doi: 10.1109/TCYB.2019.2915253
    [36]
    Q. Hu, S. Wang, Z. Xiong, and X. Cheng, “Nothing wasted: Full contribution enforcement in federated edge learning,” IEEE Trans. Mob. Comput., vol. 22, no. 5, pp. 2850–2861, May 2023. doi: 10.1109/TMC.2021.3123195
    [37]
    Q. Hu, Z. Wang, M. Xu, and X. Cheng, “Blockchain and federated edge learning for privacy-preserving mobile crowdsensing,” IEEE Internet Things J., vol. 10, no. 14, pp. 12000–12011, Jul. 2023. doi: 10.1109/JIOT.2021.3128155
    [38]
    J. Chen, Q. Hu, and H. Jiang, “Social welfare maximization in cross-silo federated learning,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process., Singapore, 2022, pp. 4258–4262.
    [39]
    W. Yu, G. Ginis, and J. Cioffi, “Distributed multiuser power control for digital subscriber lines,” IEEE J. Sel. Areas. Commun., vol. 20, no. 5, pp. 1105–1115, Jun. 2002. doi: 10.1109/JSAC.2002.1007390
    [40]
    L. Deng, “The MNIST database of handwritten digit images for machine learning research,” IEEE Signal Process. Mag., vol. 29, no. 6, pp. 141–142, Nov. 2012. doi: 10.1109/MSP.2012.2211477
    [41]
    Y. Abouelnaga, O. Ali, H. Rady, and M. Moustafa, “CIFAR-10: KNN-based ensemble of classifiers,” in Proc. IEEE Int. Conf. Comput. Sci. Comput. Intell., Las Vegas, USA, 2016, pp. 1192–1195.
    [42]
    S. Pal and S. Mitra, “Multilayer perceptron, fuzzy sets, and classification,” IEEE Trans. Neural Networks, vol. 3, no. 5, pp. 683–697, Sept. 1992. doi: 10.1109/72.159058
    [43]
    K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Comput. Soc. Conf. Comput. Vision Pattern Recognit., Las Vegas, NV, USA, 2016, pp. 770–778.
    [44]
    B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. Arcas, “Communication-efficient learning of deep networks from decentralized data,” Proc. Int. Conf. Artif. Intell. Stat., vol. 54, pp. 1273–1282, Apr. 2017.
    [45]
    C. Hilbe, M. Nowak, and K. Sigmund, “Evolution of extortion in iterated prisoner’s dilemma games,” Proc. Nat. Acad. Sci. USA, vol. 110, no. 17, pp. 6913–6918, Aug. 2013. doi: 10.1073/pnas.1214834110
    [46]
    M. Nowak and K. Sigmund, “Tit for tat in heterogeneous populations,” Nature, vol. 355, pp. 250–253, Jan. 1992. doi: 10.1038/355250a0
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(7)  / Tables(6)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (648) PDF downloads(104) Cited by()

    Highlights

    • We model the interaction among participants in the FL as a continuous iterative game, based on which the ZD (Zero-determinant) strategies are extended to the CZD (Continuous Zero-determinant) strategies. In fact, the CZD strategies are more suitable than the ZD strategies to demonstrate the incomplete cooperation scenario of FL
    • We design an incentive mechanism for FL based on the CZD strategies, which can not only motivate as many devices as possible to contribute high-quality data in FL, but also enhance the efficiency of FL. Compared with the existing ZD-based studies, our proposed approach can achieve broader incentive range, more efficient motivation, more effective incentive compatibility, and more accurate fair distribution of rewards
    • We combine numerical and real experiments to validate the advantages of the proposed method in simulations. On one hand, the strengths of the CZD strategies are proved by numerical experiments. On the other hand, the effectiveness of the CZD-based incentive algorithm is verified by FL experiments with real datasets

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return