Communication-Computation Trade-Off in Resource-Constrained Edge Inference

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 computation cost of the on-device model and the communication cost of forwarding the intermediate feature to the edge server. A three-step framework is proposed for the effective inference: (1) model split point selection to determine the on-device model, (2) communication-aware model compression to reduce the on-device computation and the resulting communication overhead simultaneously, and (3) task-oriented encoding of the intermediate feature to further reduce the communication overhead. Experiments demonstrate that our proposed framework achieves a better trade-off and significantly reduces the inference latency than baseline methods.

arXiv commentThis work has been submitted to the IEEE for possible publication

References in corpus (5)

• Neural Discrete Representation Learning
• To prune, or not to prune: exploring the efficacy of pruning for model compression
• JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution
• Neural Joint Source-Channel Coding
• Communication-Efficient Edge AI: Algorithms and Systems

Cited by in corpus (3)

• Capacity of Remote Classification Over Wireless Channels
• Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems
• Branchy-GNN: a Device-Edge Co-Inference Framework for Efficient Point Cloud Processing