Adaptive Split Learning over Energy-Constrained Wireless Edge Networks
This work addresses training delay and energy consumption issues for devices in energy-constrained wireless edge networks, representing an incremental improvement over existing split learning schemes.
The paper tackles the inefficiency of fixed split points in split learning for wireless edge networks by proposing an adaptive scheme that dynamically selects split points and allocates computing resources, resulting in a 53.7% reduction in average training delay and a 22.1% reduction in energy consumption compared to existing methods.
Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the device heterogeneity and variation of channel conditions, this way is not optimal in training delay and energy consumption. In this paper, we design an adaptive split learning (ASL) scheme which can dynamically select split points for devices and allocate computing resource for the server in wireless edge networks. We formulate an optimization problem to minimize the average training latency subject to long-term energy consumption constraint. The difficulties in solving this problem are the lack of future information and mixed integer programming (MIP). To solve it, we propose an online algorithm leveraging the Lyapunov theory, named OPEN, which decomposes it into a new MIP problem only with the current information. Then, a two-layer optimization method is proposed to solve the MIP problem. Extensive simulation results demonstrate that the ASL scheme can reduce the average training delay and energy consumption by 53.7% and 22.1%, respectively, as compared to the existing SL schemes.