Spatio-Temporal Split Learning

TL;DR

This paper introduces a spatio-temporal split learning framework that enables multiple end-systems to collaboratively train neural networks while preserving data privacy, combining spatial and temporal separation of computation.

Contribution

It presents a novel split learning architecture with multiple end-systems sharing a centralized server, enhancing privacy and efficiency over traditional methods.

Findings

Achieves near-optimal accuracy in privacy-preserving neural network training.

Effectively combines spatial and temporal separation for data privacy.

Demonstrates practical viability through performance evaluation.

Abstract

This paper proposes a novel split learning framework with multiple end-systems in order to realize privacypreserving deep neural network computation. In conventional split learning frameworks, deep neural network computation is separated into multiple computing systems for hiding entire network architectures. In our proposed framework, multiple computing end-systems are sharing one centralized server in split learning computation, where the multiple end-systems are with input and first hidden layers and the centralized server is with the other hidden layers and output layer. This framework, which is called as spatio-temporal split learning, is spatially separated for gathering data from multiple end-systems and also temporally separated due to the nature of split learning. Our performance evaluation verifies that our proposed framework shows nearoptimal accuracy while preserving data privacy.