Exploring Edge-Driven Collaborative Fine-Tuning Toward Customized AIGC Services
IEEE Network · 2025-05 · 39 (3) · 293-301
DOI: 10.1109/mnet.2024.3441040 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Network, 2025-05. Verfasst von Qinnan Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 15 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Uniate State National Science Foundation, U.S National Science Foundation under Grants.
Abstract (Originalsprache)
With the popularization of artificial intelligence-generated content (AIGC), the explosion of end users is spurring an unprecedented diversity in preferences. To cope with this challenge, the AIGC paradigm is shifting from cloud-driven pre-trained large models to edge-driven personalized customization models. The former are large-scale models with more than 100 billion parameters trained based on massive data, while the latter introduce heterogeneous user preferences or professional knowledge to fine-tune the former. However, such fine-tuning incurs costly resource consumption and privacy disclosure. In this paper, we offer a holistic perspective on the AIGC fine-tuning framework spanning from end user to edge to cloud. Specifically, we first investigate how to deploy an edge-driven collaborative fine-tuning task through federated learning. Then, we discuss a verifiable model consensus protocol and fairness incentive design for edge servers to participate in a collaborative learning task. In addition, a case study focuses on the medical scenario, where we develop a practical X-ray diagnostic demo through collaborative fine-tuning of a multimodal pre-training model, and the diagnostic dialogue and performance results are compared. Finally, potential research directions are identified to advance the edge-driven customized AIGC services.
Förderung
- National Natural Science Foundation of China
- Uniate State National Science Foundation
- U.S National Science Foundation under Grants
- MU-SUTD Joint Grant
- SUTD Kickstarter Initiative
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Zhang, Q., Zong, T., Xiong, Z., Sun, P., Zhu, J., Qiu, W., Zheng, Z., & Poor, H. V. (2025). Exploring Edge-Driven Collaborative Fine-Tuning Toward Customized AIGC Services. IEEE Network, 39(3), 293-301. https://doi.org/10.1109/mnet.2024.3441040
Vancouver
Zhang Q, Zong T, Xiong Z, Sun P, Zhu J, Qiu W, et al. Exploring Edge-Driven Collaborative Fine-Tuning Toward Customized AIGC Services. IEEE Network. 2025;39(3):293-301. doi:10.1109/mnet.2024.3441040
BibTeX
@article{Zhang2025,
author = {Zhang, Qinnan and Zong, Tianqi and Xiong, Zehui and Sun, Pangbo and Zhu, Jianming and Qiu, Wangjie and Zheng, Zhiming and Poor, H. Vincent},
title = {Exploring Edge-Driven Collaborative Fine-Tuning Toward Customized AIGC Services},
journal = {IEEE Network},
year = {2025},
volume = {39},
number = {3},
pages = {293--301},
doi = {10.1109/mnet.2024.3441040}
}
EUVIMED