BriefGPT.xyz
May, 2021
通过平衡通信折衷来实现快速联邦学习
Fast Federated Learning by Balancing Communication Trade-Offs
HTML
PDF
Milad Khademi Nori, Sangseok Yun, Il-Min Kim
TL;DR
根据局部更新系数和梯度压缩稀疏预算之间的权衡方式,提出了一种新的快速联邦学习方案(Fast FL),该方案通过动态地调整这两种变量来实现最小化学习误差。结果表明,Fast FL能够快速且一致地实现比文献中类似方案更高的精确度。
Abstract
federated learning
(FL) has recently received a lot of attention for large-scale
privacy-preserving
machine learning. However, high communication overheads due to frequent gradient transmissions decelerate FL. To
→