Federated Vision-Language-Recommendation with Personalized Fusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (28) · 23337-23345
DOI: 10.1609/aaai.v40i28.39503 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhiwei Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Applying large pre-trained Vision-Language Models to recommendation is a burgeoning field, a direction we term Vision-Language-Recommendation (VLR). Bringing VLR to user-oriented on-device intelligence within a federated learning framework is a crucial step for enhancing user privacy and delivering personalized experiences. This paper introduces FedVLR, a federated VLR framework specially designed for user-specific personalized fusion of vision-language representations. At its core is a novel bi-level fusion mechanism: The server-side multi-view fusion module first generates a diverse set of pre-fused multimodal views. Subsequently, each client employs a user-specific mixture-of-expert mechanism to adaptively integrate these views based on individual user interaction history. This designed lightweight personalized fusion module provides an efficient solution to implement a federated VLR system. The effectiveness of our proposed FedVLR has been validated on seven benchmark datasets.
Zitieren
APA
Li, Z., Long, G., Jiang, J., Zhang, C., & Yang, Q. (2026). Federated Vision-Language-Recommendation with Personalized Fusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(28), 23337-23345. https://doi.org/10.1609/aaai.v40i28.39503
Vancouver
Li Z, Long G, Jiang J, Zhang C, Yang Q. Federated Vision-Language-Recommendation with Personalized Fusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(28):23337-23345. doi:10.1609/aaai.v40i28.39503
BibTeX
@article{Li2026,
author = {Li, Zhiwei and Long, Guodong and Jiang, Jing and Zhang, Chengqi and Yang, Qiang},
title = {Federated Vision-Language-Recommendation with Personalized Fusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {28},
pages = {23337--23345},
doi = {10.1609/aaai.v40i28.39503}
}
EUVIMED