BriefGPT.xyz
Feb, 2024
DFML:分散式联邦互联学习
DFML: Decentralized Federated Mutual Learning
HTML
PDF
Yasser H. Khalil, Amir H. Estiri, Mahdi Beitollahi, Nader Asadi, Sobhan Hemati...
TL;DR
我们提出了一种无服务器的去中心化联邦互联模型学习(DFML)框架,通过相互学习和循环改变监督和蒸馏信号的量,有效处理模型和数据异构性,并在各种条件下,在收敛速度和全局准确性上优于流行基准。
Abstract
In the realm of real-world devices, centralized servers in
federated learning
(FL) present challenges including communication bottlenecks and susceptibility to a single point of failure. Additionally, contemporary devices inherently exhibit
→