This website requires JavaScript.

Learning-Based Client Selection for Federated Learning Services Over Wireless Networks with Constrained Monetary Budgets

Zhipeng ChengXuwei FanMinghui LiwangNing ChenXianbin Wang
Aug 2022
摘要
We investigate a data quality-aware dynamic client selection problem formultiple federated learning (FL) services in a wireless network, where eachclient has dynamic datasets for the simultaneous training of multiple FLservices and each FL service demander has to pay for the clients withconstrained monetary budgets. The problem is formalized as a non-cooperativeMarkov game over the training rounds. A multi-agent hybrid deep reinforcementlearning-based algorithm is proposed to optimize the joint client selection andpayment actions, while avoiding action conflicts. Simulation results indicatethat our proposed algorithm can significantly improve the training performance.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答