在本次工作中，我們介紹了分裂網絡驅動的垂直分區，這是一種分布式深度學習方法的配置，稱為SplitN，以友善從垂直分布特征中學習。SplitNN不與合作機構共享原始資料或模型細節。拟議的配置允許在持有不同資料源的機構之間進行瞄準，而不需要複雜的加密算法或安全計算協定。我們評估幾種配置來合并分割模型的輸出，并比較性能和資源效率。該方法非常靈活，允許使用多種不同的配置來解決垂直拆分資料集所帶來的具體問題。
原文題目：SplitNN-driven Vertical Partitioning
原文：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.
原文作者:Iker Ceballos, Vivek Sharma, Eduardo Mugica, Abhishek Singh, Alberto Roman, Praneeth Vepakomma, Ramesh Raskar
原文位址：https://arxiv.org/abs/2008.04137
SplitNN-driven垂直分區(CS).pdf