Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Dongwon, Seo, Jiwan, Kang, Joonhyuk
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.19360
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908613988057088
author Kim, Dongwon
Seo, Jiwan
Kang, Joonhyuk
author_facet Kim, Dongwon
Seo, Jiwan
Kang, Joonhyuk
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19360
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Rate Task-Oriented Communication for Multi-Edge Cooperative Inference
Kim, Dongwon
Seo, Jiwan
Kang, Joonhyuk
Signal Processing
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.
title Multi-Rate Task-Oriented Communication for Multi-Edge Cooperative Inference
topic Signal Processing
url https://arxiv.org/abs/2510.19360