BriefGPT.xyz
Oct, 2023
面向轻量通信设计的联邦学习压缩
Federated learning compression designed for lightweight communications
HTML
PDF
Lucas Grativol Ribeiro, Mathieu Leonardon, Guillaume Muller, Virginie Fresse, Matthieu Arzel
TL;DR
本文研究压缩技术对典型图像分类任务的联邦学习的影响，并证明了一种简单的方法可以在保持不到1%准确率损失的同时压缩50%的消息，与最先进的技术相媲美。
Abstract
federated learning
(FL) is a promising distributed method for
edge-level machine learning
, particularly for privacysensitive applications such as those in military and medical domains, where client data cannot be
→