Federated Vision-Language-Recommendation with Personalized Fusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909881133432832 |
|---|---|
| author | Li, Zhiwei Long, Guodong Jiang, Jing Zhang, Chengqi Yang, Qiang |
| author_facet | Li, Zhiwei Long, Guodong Jiang, Jing Zhang, Chengqi Yang, Qiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08478 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Federated Vision-Language-Recommendation with Personalized Fusion Li, Zhiwei Long, Guodong Jiang, Jing Zhang, Chengqi Yang, Qiang Information Retrieval Artificial Intelligence Machine Learning 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. |
| title | Federated Vision-Language-Recommendation with Personalized Fusion |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.08478 |