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 

机构地区：[1]Cyberspace Institute of Advanced Technology,Guangzhou University,Guangzhou,510006,China [2]School of Cyber Science and Engineering,Huazhong University of Science and Technology,Wuhan,430074,China [3]China Industrial Control Systems Cyber Emergency Response Team,Beijing,100040,China

出　　处：《Digital Communications and Networks》2024年第2期389-403,共15页数字通信与网络（英文版）

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).

摘　　要：Benefiting from the development of Federated Learning(FL)and distributed communication systems,large-scale intelligent applications become possible.Distributed devices not only provide adequate training data,but also cause privacy leakage and energy consumption.How to optimize the energy consumption in distributed communication systems,while ensuring the privacy of users and model accuracy,has become an urgent challenge.In this paper,we define the FL as a 3-layer architecture including users,agents and server.In order to find a balance among model training accuracy,privacy-preserving effect,and energy consumption,we design the training process of FL as game models.We 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 game.The 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 FL.Following 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.

关 键 词：Federated learning Privacy preservation Energy optimization Game theory Distributed communication systems 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]