BriefGPT.xyz
Apr, 2021
关于网络内学习的比较研究：与联邦学习和分割学习的对比
On In-network learning. A Comparative Study with Federated and Split Learning
HTML
PDF
Matei Moldoveanu, Abdellatif Zaidi
TL;DR
本文探讨通过在无线网络中分布式提取特征，使用“网络内学习”来进行推理的问题。我们详细阐述了我们提出的体系结构，提供了一种适当的损失函数，并讨论了使用神经网络进行优化的方法。我们比较了其性能与联邦和分散学习相比，并展示了该体系结构提供更好的准确性和节省带宽。
Abstract
In this paper, we consider a problem in which distributively extracted features are used for performing inference in
wireless networks
. We elaborate on our proposed architecture, which we herein refer to as "
in-network
→