Spatio-Temporal Split Learning
This work addresses privacy concerns in distributed deep learning for applications involving multiple data sources, though it appears incremental as it builds upon existing split learning frameworks.
The paper tackles the problem of privacy-preserving deep neural network computation by proposing a spatio-temporal split learning framework with multiple end-systems and a centralized server, achieving near-optimal accuracy while preserving data privacy.
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.