Contract Theory Based Incentive Mechanism for Clustered Vehicular Federated Learning

被引:3
作者
Wang, Siyang [1 ,2 ]
Zhao, Haitao [1 ,2 ]
Wen, Wanli [3 ]
Xia, Wenchao [1 ,2 ]
Wang, Bin [4 ]
Zhu, Hongbo [1 ,2 ]
机构
[1] Nanjing Univ Posts & Telecommun, Jiangsu Key Lab Wireless Commun, Nanjing 210003, Peoples R China
[2] Nanjing Univ Posts & Telecommun, Engn Res Ctr Hlth Serv Syst Based Ubiquitous Wirel, Minist Educ, Nanjing 210003, Peoples R China
[3] Chongqing Univ, Sch Microelect & Commun Engn, Chongqing 400044, Peoples R China
[4] Zhejiang Univ, Coll Elect Engn, Hangzhou 310058, Peoples R China
基金
中国国家自然科学基金;
关键词
Internet of Vehicles; federated learning; clustering; incentive mechanism; contract theory; DESIGN; EDGE;
D O I
10.1109/TITS.2024.3376792
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Clustered Vehicular Federated Learning (CVFL) can be used to improve traffic safety, increase traffic efficiency, and reduce vehicle carbon emissions. Therefore, it is extremely promising in intelligent transportation systems. However, in practice, it is difficult to accurately cluster vehicular clients with mobility according to data distribution. In addition, vehicular clients may be reluctant to contribute their computation and communication resources to perform learning tasks if the CVFL server does not give them proper incentives. In this paper, we would like to address the above issues. Specifically, considering the mobility of vehicular clients, we first propose a clustering method to cluster vehicular clients into several clusters based on the cosine similarity between the model gradient of local vehicular clients and the K-means method. Then, we design a set of optimal contracts specifically for the clusters, aiming to motivate them to select the optimal number of intra-cluster iterations for model training and give the closed-form solution to the contracts under the constraints of individual rationality, incentive compatibility, and task accuracy. The proposed contract theory based incentive mechanism not only effectively motivates every cluster, but also overcomes the information asymmetry problem to maximize the utility of the CVFL server. Finally, simulation results validate the effectiveness of the proposed clustering method and the designed contract.
引用
收藏
页码:8134 / 8147
页数:14
相关论文
共 50 条
[41]   Incentivizing Semisupervised Vehicular Federated Learning: A Multidimensional Contract Approach With Bounded Rationality [J].
Ye, Dongdong ;
Huang, Xumin ;
Wu, Yuan ;
Yu, Rong .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (19) :18573-18588
[42]   Distributed Mechanism Design in Continuous Space for Federated Learning Over Vehicular Networks [J].
Montazeri, Mina ;
Kebriaei, Hamed ;
Araabi, Babak N. ;
Kang, Jiawen ;
Niyato, Dusit .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (04) :4196-4206
[43]   A Hierarchical Incentive Mechanism for Coded Federated Learning [J].
Ng, Jer Shyuan ;
Lim, Wei Yang Bryan ;
Xiong, Zehui ;
Deng, Xianjun ;
Zhang, Yang ;
Niyato, Dusit ;
Leung, Cyril .
2021 17TH INTERNATIONAL CONFERENCE ON MOBILITY, SENSING AND NETWORKING (MSN 2021), 2021, :17-24
[44]   FlwrBC: Incentive Mechanism Design for Federated Learning by Using Blockchain [J].
Cam, Nguyen Tan ;
Kiet, Vu Tuan .
IEEE ACCESS, 2023, 11 :107855-107866
[45]   A Novel Incentive Mechanism for Federated Learning Over Wireless Communications [J].
Wang Y. ;
Zhou Y. ;
Huang P. .
IEEE. Trans. Artif. Intell., 11 (5561-5574) :5561-5574
[46]   Byzantine-robust federated learning with ensemble incentive mechanism [J].
Zhao, Shihai ;
Pu, Juncheng ;
Fu, Xiaodong ;
Liu, Li ;
Dai, Fei .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2024, 159 :272-283
[47]   Incentive Mechanism Design for Joint Resource Allocation in Blockchain-Based Federated Learning [J].
Wang, Zhilin ;
Hu, Qin ;
Li, Ruinian ;
Xu, Minghui ;
Xiong, Zehui .
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 34 (05) :1536-1547
[48]   Contribution Matching-Based Hierarchical Incentive Mechanism Design for Crowd Federated Learning [J].
Zhang, Hangjian ;
Jin, Yanan ;
Lu, Jianfeng ;
Cao, Shuqin ;
Dai, Qing ;
Yang, Shasha .
IEEE ACCESS, 2024, 12 :24735-24750
[49]   Portfolio-Based Incentive Mechanism Design for Cross-Device Federated Learning [J].
Yang, Jiaxi ;
Cao, Sheng ;
Zhao, Cuifang ;
Niu, Weina ;
Tsai, Li-Chuan .
2024 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC 2024, 2024,
[50]   A Stackelberg Incentive Mechanism for Wireless Federated Learning With Differential Privacy [J].
Yi, Zhenning ;
Jiao, Yutao ;
Dai, Wenting ;
Li, Guoxin ;
Wang, Haichao ;
Xu, Yuhua .
IEEE WIRELESS COMMUNICATIONS LETTERS, 2022, 11 (09) :1805-1809