基于多维拍卖与主从博弈的联邦学习激励机制
An incentive mechanism of multi-dimensional auction and Stackelberg game for federated learning
江帆 1陈紫东 2王军选 1禹忠1
作者信息
- 1. 西安邮电大学 通信与信息工程学院,陕西 西安 710121;陕西省信息通信网络及安全重点实验室,陕西 西安 710121
- 2. 西安邮电大学 通信与信息工程学院,陕西 西安 710121
- 折叠
摘要
为了在复杂的用户成本与有限的基站预算下保证训练用户持续参与整个联邦学习训练过程,提出一种基于多维拍卖与主从博弈模型的联邦学习激励机制.该机制结合用户自身的数据质量、数量及历史声誉等指标,采用多维拍卖法从所有拟参与拍卖的用户中选出排名前K名的用户参与联邦学习训练过程.利用主从博弈法得到基站的最优奖励和训练用户的最佳训练成本,并确定双方博弈的纳什均衡解.仿真结果表明,与固定激励机制及无激励机制相比,在数据独立同分布(Independent Identically Distributed,IID)和非独立同分布(Non-Independent Identically Distributed,Non-IID)情况下,所提机制的准确率与全局训练损失均优于对比机制,能够保证训练用户持续参与整个联邦学习训练过程.
Abstract
In order to ensure that the training users can continuously participate in the whole federa-ted learning and training process under the limited base station budget,a federated learning incentive mechanism based on multi-dimensional auction and Stackelberg game model is proposed.Combined with the user's own data quality,quantity and historical reputation,the mechanism uses the multi-dimensional auction method to select the top K users from all the users who intend to participate in the auction,to participate in the federated learning training process.The Stackelberg game method is used to obtain the optimal reward of the base station and the optimal training cost of the training us-er,and the Nash equilibrium solution of the game between the two sides is determined.Simulation results show that compared with the fixed incentive mechanism and the unincentive mechanism,the accuracy and global training loss of the proposed mechanism are better than those of the comparison mechanisms,which can guarantee that the training users will continuously participate in the whole federated learning and training process with data of independent identically distribution(IID)and non-independent identically distribution(Non-IID)data,which ensures that the training user can continuously participate in the whole federated learning and training process.
关键词
移动边缘计算/联邦学习/多维拍卖/主从博弈/纳什均衡Key words
mobile edge computing/federated learning/multi-dimensional auctions/Stackelberg game/Nash equilibrium引用本文复制引用
基金项目
国家自然科学基金(62071377)
国家自然科学基金(62101442)
国家自然科学基金(62201456)
陕西省工业攻关项目(2023-YBGY-036)
西安邮电大学创新基金(CXJJZL2022002)
出版年
2024
NETL
NSTL
万方数据