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

TL;DR

This paper introduces SplitNN, a distributed deep learning method enabling health institutions to collaboratively train models without sharing raw patient data, addressing privacy concerns while maintaining performance.

Contribution

It proposes multiple configurations of SplitNN tailored for various healthcare data sharing scenarios, enhancing privacy-preserving collaborative learning.

Findings

SplitNN outperforms federated learning in certain settings.

SplitNN reduces data sharing risks while maintaining model accuracy.

Efficient resource utilization demonstrated in experiments.

Abstract

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.