EUVIMEDEUVIMED entdecken
Crossref

Fast Multimodal Edge Inference via Selective Feature Distillation

Jinyu Chen, Wenchao Xu, Yunfeng Fan, Haozhao Wang, Quan Chen, Jing Li

IEEE Transactions on Mobile Computing · 2025-11 · 24 (11) · 11337-11350

DOI: 10.1109/tmc.2025.3580102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-11. Verfasst von Jinyu Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Post-Doc Fellowship Award from the Hong Kong RGC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Inferring user status at the edge is essential for delivering personalized services, such as detecting emotional states. However, deploying large-scale models directly on user devices is impractical due to substantial computational overhead and the scarcity of labeled data. Conversely, uploading raw data to the cloud for processing raises significant privacy concerns and incurs prohibitive communication costs. To address this challenge, we propose a privacy-preserving multimodal inference framework that leverages large-scale public data while safeguarding sensitive information and optimizing computational efficiency. Specifically, we first train a teacher model in the cloud using publicly available data. Through a feature distillation process, the knowledge from this teacher model is transferred to a lightweight encoder deployed at the user end. This transfer is tailored to the user’s data, ensuring that only relevant knowledge is distilled. To accommodate varying communication constraints, we introduce a feature compression mechanism that significantly reduces communication overhead without compromising inference accuracy. Extensive experiments on emotion recognition tasks demonstrate that the proposed framework effectively balances privacy preservation, resource efficiency, and inference accuracy, facilitating seamless collaboration between cloud and edge devices.

Förderung

  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Post-Doc Fellowship Award from the Hong Kong RGC
  • Research Grants Council of the Hong Kong Special Administrative Region, China

Zitieren

APA

Chen, J., Xu, W., Fan, Y., Wang, H., Chen, Q., & Li, J. (2025). Fast Multimodal Edge Inference via Selective Feature Distillation. IEEE Transactions on Mobile Computing, 24(11), 11337-11350. https://doi.org/10.1109/tmc.2025.3580102

Vancouver

Chen J, Xu W, Fan Y, Wang H, Chen Q, Li J. Fast Multimodal Edge Inference via Selective Feature Distillation. IEEE Transactions on Mobile Computing. 2025;24(11):11337-11350. doi:10.1109/tmc.2025.3580102

BibTeX
@article{Chen2025,
  author = {Chen, Jinyu and Xu, Wenchao and Fan, Yunfeng and Wang, Haozhao and Chen, Quan and Li, Jing},
  title = {Fast Multimodal Edge Inference via Selective Feature Distillation},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2025},
  volume = {24},
  number = {11},
  pages = {11337--11350},
  doi = {10.1109/tmc.2025.3580102}
}
Kostenlos starten →