BriefGPT.xyz
Jun, 2022
自适应专家模型用于联邦学习中的个性化
Adaptive Expert Models for Personalization in Federated Learning
HTML
PDF
Martin Isaksson, Edvin Listo Zec, Rickard Cöster, Daniel Gillblad, Šarūnas Girdzijauskas
TL;DR
该研究提出了一种针对非IID数据的个性化联邦学习方法，使用专家混合模型来学习相似的客户，即使在病理性非IID环境中，我们的方法仍然能够比本地模型获得高达4.38％的精度优势。
Abstract
federated learning
(FL) is a promising framework for
distributed learning
when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous a
→