EUVIMEDEUVIMED entdecken
Crossref

Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication With Visual Feature Alignment

Songjie Xie, Hengtao He, Shenghui Song, Jun Zhang, Khaled B. Letaief

IEEE Journal on Selected Areas in Communications · 2025-12 · 43 (12) · 4262-4276

DOI: 10.1109/jsac.2025.3623175 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2025-12. Verfasst von Songjie Xie und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Hong Kong Research Grants Council (RGC) through the Areas of Excellence Scheme, General Research Fund from Hong Kong RGC, NSFC/RGC Joint Research Scheme through the RGC of Hong Kong Special Administrative Region, China, and the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Task-oriented communication presents a promising approach to improve the communication efficiency of edge inference systems by optimizing learning-based modules to extract and transmit relevant task information. However, real-time applications face practical challenges, such as incomplete coverage and potential malfunctions of edge servers. This situation necessitates cross-model communication between different inference systems, enabling edge devices from one service provider to collaborate effectively with edge servers from another. Independent optimization of diverse edge systems often leads to incoherent feature spaces, which hinders the cross-model inference for existing task-oriented communication. To facilitate and achieve effective cross-model task-oriented communication, this study introduces a novel framework that utilizes shared anchor data across diverse systems. This approach addresses the challenge of feature alignment in both server-based and on-device scenarios. In particular, by leveraging the linear invariance of visual features, we propose efficient server-based feature alignment techniques to estimate linear transformations using encoded anchor data features. For on-device alignment, we exploit the angle-preserving nature of visual features and propose to encode relative representations with anchor data to streamline cross-model communication without additional alignment procedures during the inference. The experimental results on computer vision benchmarks demonstrate the superior performance of the proposed feature alignment approaches in cross-model task-oriented communications. The runtime and computation overhead analysis further confirm the effectiveness of the proposed feature alignment approaches in real-time applications.

Förderung

  • Hong Kong Research Grants Council (RGC) through the Areas of Excellence Scheme
  • General Research Fund from Hong Kong RGC
  • NSFC/RGC Joint Research Scheme through the RGC of Hong Kong Special Administrative Region, China, and the National Natural Science Foundation of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province

Zitieren

APA

Xie, S., He, H., Song, S., Zhang, J., & Letaief, K. B. (2025). Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication With Visual Feature Alignment. IEEE Journal on Selected Areas in Communications, 43(12), 4262-4276. https://doi.org/10.1109/jsac.2025.3623175

Vancouver

Xie S, He H, Song S, Zhang J, Letaief KB. Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication With Visual Feature Alignment. IEEE Journal on Selected Areas in Communications. 2025;43(12):4262-4276. doi:10.1109/jsac.2025.3623175

BibTeX
@article{Xie2025,
  author = {Xie, Songjie and He, Hengtao and Song, Shenghui and Zhang, Jun and Letaief, Khaled B.},
  title = {Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication With Visual Feature Alignment},
  journal = {IEEE Journal on Selected Areas in Communications},
  year = {2025},
  volume = {43},
  number = {12},
  pages = {4262--4276},
  doi = {10.1109/jsac.2025.3623175}
}
Kostenlos starten →