arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.00564cs.LGstat.ML
收藏

分割学习促进健康:分布式深度学习,无需共享原始患者数据

Split learning for health: Distributed deep learning without sharing raw patient data

Massachusetts Institute of Technology(麻省理工学院)

Praneeth Vepakomma, Otkrist Gupta, Tristan Swedish, Ramesh Raskar

摘要:

卫生实体能否在不共享敏感原始数据的情况下协作训练深度学习模型?本文提出了一种称为SplitNN的分布式深度学习方法的几种配置,以促进这种协作。SplitNN不与合作机构共享原始数据或模型细节。splitNN的拟议配置迎合了以下实际设置:i)持有不同模式的患者数据的实体,ii)在多个任务上协作的集中式和本地健康实体,以及iii)在不共享标签的情况下学习。我们比较了splitNN和其他分布式深度学习方法(如联邦学习、大批量同步随机梯度下降)的性能和资源效率权衡,并显示了splitNN非常令人鼓舞的结果。

英文摘要:

Can health entities collaboratively train deep learning models without sharing sensitive raw data? This paper proposes several configurations of a distributed deep learning method called SplitNN to facilitate such collaborations. SplitNN does not share raw data or model details with collaborating institutions. The proposed configurations of splitNN cater to practical settings of i) entities holding different modalities of patient data, ii) centralized and local health entities collaborating on multiple tasks and iii) learning without sharing labels. We compare performance and resource efficiency trade-offs of splitNN and other distributed deep learning methods like federated learning, large batch synchronous stochastic gradient descent and show highly encouraging results for splitNN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑