BriefGPT.xyz
Nov, 2024
基于特征分布适应的个性化联邦学习
Personalized Federated Learning via Feature Distribution Adaptation
HTML
PDF
Connor J. Mclaughlin, Lili Su
TL;DR
本研究解决了传统联邦学习在异构客户端下训练结果不稳定的问题。提出了一种新颖的方法,将表示学习视为生成建模任务,并通过算法pFedFDA有效生成适应本地特征分布的个性化模型。通过广泛的计算机视觉基准测试,证明该方法在数据稀缺环境下显著优于现有最先进技术。
Abstract
Federated Learning
(FL) is a distributed learning framework that leverages commonalities between distributed client datasets to train a global model. Under heterogeneous clients, however, FL can fail to produce stable training results. Personalized
→