BriefGPT.xyz
Oct, 2021
用户中心联邦学习
User-Centric Federated Learning
HTML
PDF
Mohamad Mestoukirdi, Matteo Zecchin, David Gesbert, Qianrui Li, Nicolas Gresset
TL;DR
本研究提出了一种使用多个以用户为中心的聚合规则实现个性化的联邦学习方法，通过广播协议来限制个性化流的数量从而在保证学习效果的情况下提高通信效率。仿真结果表明与其他竞争的基准方案相比，我们的方法具有更高的个性化能力、更快的收敛速度和更好的通信效率。
Abstract
data heterogeneity
across participating devices poses one of the main challenges in
federated learning
as it has been shown to greatly hamper its convergence time and generalization capabilities. In this work, we
→