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.
Cite
@article{arxiv.2410.08478,
title = {Federated Vision-Language-Recommendation with Personalized Fusion},
author = {Zhiwei Li and Guodong Long and Jing Jiang and Chengqi Zhang and Qiang Yang},
journal= {arXiv preprint arXiv:2410.08478},
year = {2025}
}