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.
@article{arxiv.2008.04137,
title = {SplitNN-driven Vertical Partitioning},
author = {Iker Ceballos and Vivek Sharma and Eduardo Mugica and Abhishek Singh and Alberto Roman and Praneeth Vepakomma and Ramesh Raskar},
journal= {arXiv preprint arXiv:2008.04137},
year = {2020}
}