Spatio-Temporal Split Learning
Joongheon Kim, Seunghoon Park, Soyi Jung, Seehwan Yoo · 2021
This paper proposes a novel split learning framework with multiple end-systems in order to realize privacy-preserving 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 near-optimal accuracy while preserving data privacy.