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

TL;DR

This paper introduces a three-step framework for optimizing edge AI inference by balancing computation and communication costs, significantly reducing latency on resource-limited devices.

Contribution

It proposes a novel framework combining model split, compression, and encoding techniques for efficient device-edge co-inference.

Findings

Achieves better trade-offs between computation and communication costs.

Reduces inference latency significantly compared to baseline methods.

Effectively balances model complexity and data transmission overhead.

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.