BriefGPT.xyz
Dec, 2023
通信高效的联邦学习系统中的遮蔽剪枝降维方法
A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems
HTML
PDF
Tamir L. S. Gez, Kobi Cohen
TL;DR
使用蒙特卡洛方法结合剪枝算法,提出了一种名为MPFL的在通信受限系统中降低模型通信成本的迭代式分布式机器学习算法。
Abstract
federated learning
(FL) represents a growing
machine learning
(ML) paradigm designed for training models across numerous nodes that retain local datasets, all without directly exchanging the underlying private da
→