A game-theoretic approach for federated learning:A trade-off among privacy,accuracy and energy

作     者：Lihua Yin Sixin Lin Zhe Sun Ran Li Yuanyuan He Zhiqiang Hao Lihua Yin;Sixin Lin;Zhe Sun;Ran Li;Yuanyuan He;Zhiqiang Hao

作者机构：Cyberspace Institute of Advanced TechnologyGuangzhou UniversityGuangzhou510006China School of Cyber Science and EngineeringHuazhong University of Science and TechnologyWuhan430074China China Industrial Control Systems Cyber Emergency Response TeamBeijing100040China 

出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)

年 卷 期：2024年第10卷第2期

页      面：389-403页

核心收录：

学科分类：0839[工学-网络空间安全] 08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：sponsored by the National Key R&D Program of China(No.2018YFB2100400) the National Natural Science Foundation of China(No.62002077,61872100) the Major Research Plan of the National Natural Science Foundation of China(92167203) the Guangdong Basic and Applied Basic Research Foundation(No.2020A1515110385) the China Postdoctoral Science Foundation(No.2022M710860) the Zhejiang Lab(No.2020NF0AB01) Guangzhou Science and Technology Plan Project(202102010440) 

主　　题：Federated learning Privacy preservation Energy optimization Game theory Distributed communication systems 

摘      要：Benefiting from the development of Federated Learning(FL)and distributed communication systems,large-scale intelligent applications become *** devices not only provide adequate training data,but also cause privacy leakage and energy *** to optimize the energy consumption in distributed communication systems,while ensuring the privacy of users and model accuracy,has become an urgent *** this paper,we define the FL as a 3-layer architecture including users,agents and *** order to find a balance among model training accuracy,privacy-preserving effect,and energy consumption,we design the training process of FL as game *** use an extensive game tree to analyze the key elements that influence the players’decisions in the single game,and then find the incentive mechanism that meet the social norms through the repeated *** experimental results show that the Nash equilibrium we obtained satisfies the laws of reality,and the proposed incentive mechanism can also promote users to submit high-quality data in *** the multiple rounds of play,the incentive mechanism can help all players find the optimal strategies for energy,privacy,and accuracy of FL in distributed communication systems.