| 10 | 0 | 0 |
 Reads |
 Downloads |
 Citas |
A cooperative game based federated learning aggregation algorithm is proposed to address the model training challenges due to client data heterogeneity and potentially malicious clients in federated learning. The method integrates personalized federated meta ⁃ learning with cooperative game Shapley value optimization strategy, which aims to improve the performance and robustness of the global model and reduce the communication and computation costs. Firstly, by collecting client soft labels, the maximum entropy judgment method is used to select the clients with high contribution to the global model. Secondly, a fast estimation strategy based on the TMC⁃Shapley value is designed to efficiently estimate the marginal contribution of clients by finite times sampling, so as to avoid exponential computational complexity. Finally, weighted aggregation is performed based on client Shapley values and data distribution characteristics. Experiments show that the proposed method performs well on the real dataset classification task, significantly improves the accuracy and reduces the computational cost in comparison with the baseline method. Its advantages are more prominent in the scenario with a large number of clients and significant data heterogeneity.
[1] McMahan B, Moore E, Ramage D, et al. Communication⁃ efficient learning of deep networks from decentralized data [C]// Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale, FL, USA: PMLR, 2017: 1273⁃1282.
[2] Ye Yutong, Zhao Wupan, Wei Tongquan, et al. FedLight: Federated reinforcement learning for autonomous multi⁃intersection traffic signal control [C]// 2021 58th ACM/IEEE Design Automation Conference (DAC). San Francisco, CA, USA: IEEE, 2021: 847⁃ 852.
[3] Wu Yuncheng, Cai Shaofeng, Xiao Xiaokui, et al. Privacy preserving vertical federated learning for tree⁃based models [EB/ OL]. [2020⁃08⁃21]. https://arxiv.org/abs/2008.06170.
[4] Liu Junxu, Lou Jian, Xiong Li, et al. Projected federated averaging with heterogeneous differential privacy [J]. Proceedings of the VLDB Endowment, 2021, 15(4): 828⁃840.
[5] Pillutla K, Kakade S M, Harchaoui Z. Robust aggregation for federated learning [J]. IEEE Transactions on Signal Processing, 2022, 70: 1142⁃1154.
[6] Karimireddy S P, Kale S, Mohri M, et al. SCAFFOLD: Stochastic controlled averaging for on⁃device federated learning [EB/OL]. [2019⁃10⁃16]. http://arxiv.org/abs/1910.06378.
[7] Li Qinbin, Diao Yiqun, Chen Quan, et al. Federated learning on non⁃IID data silos: An experimental study [C]// 2022 IEEE 38th International Conference on Data Engineering (ICDE). Kuala Lumpur, Malaysia: IEEE, 2022: 965⁃978.
[8] Chen Fei, Luo Mi, Dong Zhenhua, et al. Federated meta⁃learning with fast convergence and efficient communication [EB/OL]. [2019⁃12⁃14]. https://arxiv.org/abs/1802.07876.
[9] Jin Hongwei, Yan Ning, Mortazavi M S. Simulating aggregation algorithms for empirical verification of resilient and adaptive federated learning [C]// 2020 IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT). Leicester, the United Kingdom: IEEE, 2020: 124⁃133.
[10] Li Tian, Sahu A K, Zaheer M, et al. Federated optimization in heterogeneous networks [J]. Proceedings of Machine Learning and Systems, 2020, 2: 429⁃450.
[11] Duan Moming, Liu Duo, Chen Xianzhang, et al. Self⁃balancing federated learning with global imbalanced data in mobile systems [J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 32(1): 59⁃71.
[12] Fraboni Y, Vidal R, Kameni L, et al. Clustered sampling: Low⁃variance and improved representativity for clients selection in federated learning [C]// Proceedings of the 38th International Conference on Machine Learning. [S.l.]: PMLR, 2021: 3407⁃3416.
[13] Wu Hongda, Wang Ping. Node selection toward faster convergence for federated learning on non⁃IID data [J]. IEEE Transactions on Network Science and Engineering, 2022, 9(5): 3099⁃3111.
[14] Shapley L S. A value for n⁃person games [J]. Contribution to the Theory of Games, 1953, 2(28): 307⁃317.
[15] Sun Qiheng, Li Xiang, Zhang Jiayao, et al. ShapleyFL: Robust federated learning based on shapley value [C]// Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2023: 2096⁃2108.
[16] Hsieh K, Phanishayee A, Mutlu O, et al. The non⁃IID data quagmire of decentralized machine learning [C]// International Conference on Machine Learning. [S.l.: s.n.], 2020: 4387⁃4398.
[17] Shuai Xian, Shen Yulin, Jiang Siyang, et al. BalanceFL: Addressing class imbalance in long ⁃ tail federated learning [C]// 2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN). Milano, Italy: IEEE, 2022: 271⁃284.
[18] Finn C, Abbeel P, Levine S. Model⁃agnostic meta⁃learning for fast adaptation of deep networks [C]// International Conference on Machine Learning. Sydney, NSW, Australia: PMLR, 2017: 1126⁃1135.
[19] Li Zhenguo, Zhou Fengwei, Chen Fei, et al. Meta⁃SGD: Learning to learn quickly for few⁃shot learning [EB/OL]. [2022⁃07⁃05]. http://arxiv.org/abs/1707.09835.
[20] Zhu Zhuangdi, Hong Junyuan, Zhou Jiayu. Data⁃free knowledge distillation for heterogeneous federated learning [C]// International Conference on Machine Learning. [S.l.]: PMLR, 2021: 12878⁃12889.
[21] Tahmasebian F, Jian Lou, Li Xiong. RobustFed: a truth inference approach for robust federated learning [C]// Proceedings of the 31st ACM International Conference on Information & Knowledge Management. Atlanta, GA, USA: ACM, 2022: 1868⁃1877.
[22] Bustincio R W C, De Souza A M, Da Costa J B D, et al. EntropicFL: Efficient federated learning via data entropy and model divergence [C]// Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing. Taormina (Messina), Italy: ACM, 2023: 1⁃6.
[23] Ling Zhiwei, Yue Zhihao, Xia Jun, et al. FedEntropy: Efficient federated learning for non ⁃ IID scenarios using maximum entropy judgment ⁃ based client selection [C]// 2023 IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom). Wuhan, China: IEEE, 2023: 56⁃63.
[24] Nagalapatti L, Narayanam R. Game of gradients: Mitigating irrelevant clients in federated learning [C]// Proceedings of the Thirty⁃Fifth AAAI Conference on Artificial Intelligence. [S.l.]: AAAI, 2021: 9046⁃9054.
[25] Roth A E. The Shapley value: Essays in honor of Lloyd S. Shapley [M]. Cambridge, the United Kingdom: Cambridge University Press, 1988.
[26] Fan Zhenan, Fang Huang, Zhou Zirui, et al. Improving fairness for data valuation in horizontal federated learning [C]// 2022 IEEE 38th International Conference on Data Engineering (ICDE). Kuala Lumpur, Malaysia: IEEE, 2022: 2440⁃2453.
[27] Ghorbani A, Zou J Y. Data Shapley: Equitable valuation of data for machine learning [C]// International Conference on Machine Learning. Long Beach, California, USA: PMLR, 2019: 2242⁃2251.
[28] Wang Tianhao, Rausch J, Zhang Ce, et al. A principled approach to data valuation for federated learning [J]. Federated Learning: Privacy and Incentive, 2020, 12500: 153⁃167.
[29] Zheng Shuyuan, Cao Yang, Yoshikawa M. Secure Shapley value for cross⁃silo federated learning (technical report) [EB/ OL]. [2024⁃12⁃25]. https://arxiv.org/abs/2209.04856.
[30] Luo Jun, Wu Shandong. Adapt to adaptation: Learning personalization for cross ⁃ silo federated learning [C]// Proceedings of the Thirty⁃first International Joint Conference on Artificial Intelligence. Vienna, Austria: [s.n.], 2022: 2166⁃2173.
[31] Ma Yuhang, Xie Zhongle, Wang Jue, et al. Continual federated learning based on knowledge distillation [C]// Thirty⁃ first International Joint Conference on Artificial Intelligence. Vienna, Austria: [s.n.], 2022: 2182⁃2188.
[32] Shannon C E. A mathematical theory of communication [J]. ACM SIGMOBILE Mobile Computing and Communications Review, 2001, 5(1): 3⁃55.
[33] Dubey A, Gupta O, Raskar R, et al. Maximum⁃entropy fine grained classification [C]// Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018. Montreal, Canada: [s.n.], 2018: 635⁃645.
[34] Hinton G E, Vinyals O, Dean J. Distilling the knowledge in a neural network [EB/OL]. [2018 ⁃ 08 ⁃ 13]. http://arxiv. org/abs/ 1503.02531.
[35] Lecun Y, Bottou L, Bengio Y, et al. Gradient⁃based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278⁃2324.
[36] Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images [R]. Toronto: University of Toronto, 2009.
[37] Blanchard P, Mhamdi E, Guerraoui R, et al. Machine learning with adversaries: Byzantine tolerant gradient descent [C]// Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017. Long Beach, CA, USA: [s.n.], 2017: 119⁃129.
[38] Cao Xiaoyu, Fang Minghong, Liu Jia, et al. FLTrust: Byzantine⁃ robust federated learning via trust bootstrapping [EB/OL]. [2022⁃04⁃12]. https://arxiv.org/abs/2012.13995.
[39] Rajput S, Wang Hongyi, Charles Z B, et al. DETOX: A redundancy ⁃ based framework for faster and more robust gradient aggregation [EB/OL]. [2020⁃03⁃08]. https://arxiv.org/ abs/1907.12205.
[40] Wang Yisen, Liu Weiyang, Ma Xingjun, et al. Iterative learning with open ⁃ set noisy labels [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 8688⁃8696.
[41] Asad M, Moustafa A, Ito T. FedOpt: Towards communication efficiency and privacy preservation in federated learning [J]. Applied Sciences, 2020, 10(8): 2864.
[42] Arivazhagan M G, Aggarwal V, Singh A K, et al. Federated learning with personalization layers [EB/OL]. [2020 ⁃ 01 ⁃ 02]. http://arxiv.org/abs/1912.00818.
[43] Nguyen B L, Cao T C, Le B. Meta⁃learning and personalization layer in federated learning [C]// Asian Conference on Intelligent Information and Database Systems. Ho Chi Minh City, Vietnam: Springer, 2022: 209⁃221.
Basic Information:
DOI：10.16652/j.issn.1004⁃373x.2026.09.024
Citation Information:
[1]Liu Ying12, Li Yong13, Wen Ming2 ,et al.Cooperative game based aggregation algorithm for federated learning[J].Modern Electronic Technique,2026(9):162-171.DOI:10.16652/j.issn.1004⁃373x.2026.09.024.
Fund Information:
新疆自治区天山英才计划项目（2024TSYCCX0066）; 新疆自治区重点研发专项（2022B01007⁃1）; 新疆师范大学博士（后）科研启动基金项目（XJNUZBS2404）; 新疆自治区研究生科研创新项目（XJ2024G213）