Communication-Computation Trade-off in Resource-Constrained Edge Inference
Jiawei Shao, Jun Zhang
Abstract
The recent breakthrough in artificial intelligence (AI), especially deep neural networks (DNNs), has affected every branch of science and technology. Particularly, edge AI has been envisioned as a major application scenario to provide DNN-based services at edge devices. This article presents effective methods for edge inference at resource-constrained devices. It focuses on device-edge co-inference, assisted by an edge computing server, and investigates a critical trade-off among the computational cost of the on-device model and the communication overhead of forwarding the intermediate feature to the edge server. A general three-step framework is proposed for the effective inference: model split point selection to determine the on-device model, communication-aware model compression to reduce the on-device computation and the resulting communication overhead simultaneously, and task-oriented encoding of the intermediate feature to further reduce the communication overhead. Experiments demonstrate that our proposed framework achieves a better tradeoff and significantly reduces the inference latency than baseline methods.