Multi-Rate Task-Oriented Communication for Multi-Edge Cooperative Inference

TL;DR

This paper introduces a dynamic, rate-adaptive feature transmission framework for multi-edge AI inference, improving communication efficiency and inference accuracy under bandwidth constraints.

Contribution

It proposes a novel rate-adaptive quantization scheme combined with a dynamic programming approach for optimal code rate allocation in multi-edge inference systems.

Findings

Significantly outperforms fixed-rate schemes in experiments

Achieves better balance between communication efficiency and inference accuracy

Effectively manages limited bandwidth constraints

Abstract

The integration of artificial intelligence (AI) with the Internet of Things (IoT) enables task-oriented communication for multi-edge cooperative inference system, where edge devices transmit extracted features of local sensory data to an edge server to perform AI-driven tasks. However, the privacy concerns and limited communication bandwidth pose fundamental challenges, since simultaneous transmission of extracted features with a single fixed compression ratio from all devices leads to severe inefficiency in communication resource utilization. To address this challenge, we propose a framework that dynamically adjusts the code rate in feature extraction based on its importance to the downstream inference task by adopting a rate-adaptive quantization (RAQ) scheme. Furthermore, to select the code rate for each edge device under limited bandwidth constraint, a dynamic programming (DP) approach is leveraged to allocate the code rate across discrete code rate options. Experiments on multi-view datasets demonstrate that the proposed frameworks significantly outperform the frameworks using fixed-rate quantization, achieving a favorable balance between communication efficiency and inference performance under limited bandwidth conditions.