BriefGPT.xyz
Aug, 2020
非独立同分布数据联邦学习的反距离聚合
Inverse Distance Aggregation for Federated Learning with Non-IID Data
HTML
PDF
Yousef Yeganeh, Azade Farshad, Nassir Navab, Shadi Albarqouni
TL;DR
本研究提出了一种新颖的自适应加权方法（IDA），使用元信息来处理医疗数据中的统计异质性问题，以提高联邦学习的精度。我们在医学图像领域对IDA方法和Federated Averaging方法进行了大量分析和评估。
Abstract
federated learning
(FL) has been a promising approach in the field of
medical imaging
in recent years. A critical problem in FL, specifically in medical scenarios is to have a more accurate shared model which is
→