As a new distributed machine learning paradigm, federated learning can effectively protect data privacy in Internet of Things (IoT) applications, but it still faces challenges such as low model update efficiency and poor real-time performance. To address these issues, a new model combining distributed federated learning and coalition games is proposed, where clients collaborate in federated learning by weighing the benefits and costs of forming a coalition. Given the limited resources of devices in the IoT, a leader is selected within the coalition to coordinate the training process. To guide clients in adaptively forming coalitions while ensuring the accuracy and efficiency of model updates, a distributed coalition formation algorithm was designed. Through continuous execution of coalition mergers and splits, the ultimate coalition partition is achieved to maximize the utility of cooperative devices. To ensure a fair distribution of coalition costs, a cost allocation mechanism is proposed to maintain the stability of the algorithm's results. Finally, experimental comparisons with other strategies validate the effectiveness of the proposed model.
LEH Q, QIAOY, NGUYENL X, et al. Federated multimodal learning for IoT applications: a contrastive learning approach[C]//2023 24th Asia-Pacific Network Operations and Management Symposium (APNOMS), 2023: 201-206.
[2]
AZAMN, MICHALAL, ANSARIS, et al. Data privacy threat modelling for autonomous systems: a survey from the GDPR’s perspective[J]. IEEE Transactions on Big Data, 2023, 9(2): 388-414.
[3]
MCMAHANH B, MOOREE, RAMAGED, et al. Communication-efficient learning of deep networks from decentralized data[C]//Artificial Intelligence and Statistics, PMLR, 2017: 1273-1282.
[4]
GEORGATOSE, MAVROKEFALIDISC, BERB ERIDISK. Fully distributed federated learning with efficient local cooperations[C]//2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023: 1-5.
GUOYujiang, ZHANGZhicai. Research on federated learning of blockchain enabled multi UAV system based on reputation mechanism[J]. Journal of Test and Measurement Technology, 2024, 38(4): 345-353. (in Chinese)
[7]
TSOUVALASV, SAEEDA, OZCELEBIT, et al. Communication-efficient federated learning through adaptive weight clustering and server-side distillation[C]//2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024: 5805-5809.
[8]
HIJAZIN M, ALOQAILYM, GUIZANIM, et al. Secure federated learning with fully homomorphic encryption for IoT communications[J]. IEEE Internet of Things Journal, 2024, 11(3): 4289-4300.
[9]
CHENY A, CHENG L. An adaptive clustering scheme for client selections in communication-efficient federated learning[C]//2023 VTS Asia Pacific Wireless Communications Symposium (APWCS), 2023: 1-3.
[10]
SINGHN, TRIPATHIT, ADHIKARIM. Communication-efficient federated learning for real-time applications in edge networks[C]//2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), 2023: 527-532.
[11]
UMBREENS, SHEHZADD, SHAFIN, et al. An energy-efficient mobility-based cluster head selection for lifetime enhancement of wireless sensor networks[J]. IEEE Access, 2020, 8: 207779-207793.
[12]
NILSSONA, SMITHS, ULM G, et al. A performance evaluation of federated learning algorithms[C]//Proceedings of the Second Workshop on Distributed Infrastructures for Deep Learning, 2018: 1-8.
[13]
TRANN H, BAOW, ZOMAYAA, et al. Federated learning over wireless networks: optimization model design and analysis[C]//IEEE INFOCOM 2019-IEEE Conference on Computer Communications, 2019: 1387-1395.
FANShaoshuai, WUJianbo, TIANHui. Federated learning resource management for energy-constrained industrial IoT devices[J]. Journal on Communications, 2022, 43(8): 65-77. (in Chinese)
[16]
GAUTAMM, BENIDRISM. Coalitional game theory in power systems: applications, challenges, and future directions[C]//2023 IEEE Texas Power and Energy Conference (TPEC), 2023: 1-6.
[17]
JIANGS, WUJ. Coalition formation game in the cross-silo federated learning system[C]//2022 IEEE 19th International Conference on Mobile Ad Hoc and Smart Systems (MASS), 2022: 49-57.
[18]
RUANL, LIG, DAIW, et al. Cooperative relative localization for UAV swarm in GNSS-denied environment: a coalition formation game approach[J]. IEEE Internet of Things Journal, 2022, 9(13): 11560-11577.
[19]
NGJ S, LIMW Y B, DAIH N, et al. Joint auction-coalition formation framework for communication-efficient federated learning in UAV-enabled Internet of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(4): 2326-2344.
[20]
MASSINR, LE MARTRETC J, CIBLATP. A coalition formation game for distributed node clustering in mobile ad hoc networks[J]. IEEE Transactions on Wireless Communications, 2017, 16(6): 3940-3952.
[21]
SUNQ, LIX, ZHANGJ, et al. ShapleyFL: robust federated learning based on shapley value[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023: 2096-2108.
[22]
ZHOUY, CHAUS C K. Multi-user coalition formation for peer-to-peer energy sharing[C]//Proceedings of the Eleventh ACM International Conference on Future Energy Systems, 2020: 386-387.