COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platforms
This work addresses communication bottlenecks in split learning for IoT networks, offering a more adaptable solution for distributed learning in heterogeneous environments.
The paper tackles the challenge of communication channel conditions affecting split learning performance in IoT networks by introducing COMSPLIT, a communication-aware design that integrates early-exit strategies and handles heterogeneous devices, showing superior performance compared to vanilla SL approaches.
The significance of distributed learning and inference algorithms in Internet of Things (IoT) network is growing since they flexibly distribute computation load between IoT devices and the infrastructure, enhance data privacy, and minimize latency. However, a notable challenge stems from the influence of communication channel conditions on their performance. In this work, we introduce COMSPLIT: a novel communication-aware design for split learning (SL) and inference paradigm tailored to processing time series data in IoT networks. COMSPLIT provides a versatile framework for deploying adaptable SL in IoT networks affected by diverse channel conditions. In conjunction with the integration of an early-exit strategy, and addressing IoT scenarios containing devices with heterogeneous computational capabilities, COMSPLIT represents a comprehensive design solution for communication-aware SL in IoT networks. Numerical results show superior performance of COMSPLIT compared to vanilla SL approaches (that assume ideal communication channel), demonstrating its ability to offer both design simplicity and adaptability to different channel conditions.