arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.04137cs.LGstat.ML
收藏

SplitNN-driven垂直分区

SplitNN-driven Vertical Partitioning

Acuratio;MIT(麻省理工学院);Harvard Medical School(哈佛医学院)

Iker Ceballos, Vivek Sharma, Eduardo Mugica, Abhishek Singh, Alberto Roman, Praneeth Vepakomma, Ramesh Raskar

摘要:

在这项工作中,我们介绍了SplitNN驱动的垂直分区,这是一种称为SplitNN的分布式深度学习方法的配置,用于促进从垂直分布的特征中学习。SplitNN不与合作机构共享原始数据或模型细节。拟议的配置允许在拥有不同数据来源的机构之间进行培训,而不需要复杂的加密算法或安全计算协议。我们评估了几种配置,以合并拆分模型的输出,并比较性能和资源效率。该方法是灵活的,并允许许多不同的配置来解决垂直分割数据集带来的特定挑战。

英文摘要:

In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features. SplitNN does not share raw data or model details with collaborating institutions. The proposed configuration allows training among institutions holding diverse sources of data without the need of complex encryption algorithms or secure computation protocols. We evaluate several configurations to merge the outputs of the split models, and compare performance and resource efficiency. The method is flexible and allows many different configurations to tackle the specific challenges posed by vertically split datasets.

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。

↑