Prioritized Information Bottleneck Theoretic Framework With Distributed Online Learning for Edge Video Analytics
IEEE Transactions on Networking · 2025-06 · 33 (3) · 1203-1219
DOI: 10.1109/ton.2025.3526148 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Networking, 2025-06. Verfasst von Zhengru Fang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Hong Kong SAR Government through the Global STEM Professorship and Research Talent Hub, Hong Kong Jockey Club under Hong Kong STEM Lab of Smart City, Hong Kong Innovation and Technology Commission through InnoHK Project CIMDA.
Abstract (Originalsprache)
Collaborative perception systems leverage multiple edge devices, such as surveillance cameras or autonomous cars, to enhance sensing quality and eliminate blind spots. Despite their advantages, challenges such as limited channel capacity and data redundancy impede their effectiveness. To address these issues, we introduce the Prioritized Information Bottleneck (PIB) framework for edge video analytics. This framework prioritizes the shared data based on the signal-to-noise ratio (SNR) and camera coverage of the region of interest (RoI), reducing spatial-temporal data redundancy to transmit only essential information. This strategy avoids the need for video reconstruction at edge servers and maintains low latency. It leverages a deterministic information bottleneck method to extract compact, relevant features, balancing informativeness and communication costs. For high-dimensional data, we apply variational approximations for practical optimization. To reduce communication costs in fluctuating connections, we propose a gate mechanism based on distributed online learning (DOL) to filter out less informative messages and efficiently select edge servers. Moreover, we establish the asymptotic optimality of DOL by proving the sublinearity of its regrets. To validate the effectiveness of the PIB framework, we conduct real-world experiments on three types of edge devices with varied computing capabilities. Compared to five coding methods for image and video compression, PIB improves mean object detection accuracy (MODA) by 17.8% while reducing communication costs by 82.65% under poor channel conditions.
Förderung
- Hong Kong SAR Government through the Global STEM Professorship and Research Talent Hub
- Hong Kong Jockey Club under Hong Kong STEM Lab of Smart City
- Hong Kong Innovation and Technology Commission through InnoHK Project CIMDA
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
- Fundamental Research Funds for the Central Universities
- Research Grants Council of Hong Kong
Zitieren
APA
Fang, Z., Hu, S., Wang, J., Deng, Y., Chen, X., & Fang, Y. (2025). Prioritized Information Bottleneck Theoretic Framework With Distributed Online Learning for Edge Video Analytics. IEEE Transactions on Networking, 33(3), 1203-1219. https://doi.org/10.1109/ton.2025.3526148
Vancouver
Fang Z, Hu S, Wang J, Deng Y, Chen X, Fang Y. Prioritized Information Bottleneck Theoretic Framework With Distributed Online Learning for Edge Video Analytics. IEEE Transactions on Networking. 2025;33(3):1203-1219. doi:10.1109/ton.2025.3526148
BibTeX
@article{Fang2025,
author = {Fang, Zhengru and Hu, Senkang and Wang, Jingjing and Deng, Yiqin and Chen, Xianhao and Fang, Yuguang},
title = {Prioritized Information Bottleneck Theoretic Framework With Distributed Online Learning for Edge Video Analytics},
journal = {IEEE Transactions on Networking},
year = {2025},
volume = {33},
number = {3},
pages = {1203--1219},
doi = {10.1109/ton.2025.3526148}
}
EUVIMED