SplitNN-driven Vertical Partitioning

TL;DR

This paper introduces a novel SplitNN-driven vertical partitioning method for distributed deep learning that enables collaborative training on vertically partitioned data without sharing raw data or complex encryption, improving flexibility and efficiency.

Contribution

It proposes a new configuration of SplitNN for vertically partitioned data, eliminating the need for complex encryption and enabling flexible, resource-efficient collaborative learning.

Findings

Multiple configurations evaluated for merging split model outputs.

Performance and resource efficiency compared across configurations.

Method facilitates learning from diverse, vertically split datasets.

Abstract

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.