Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.15542 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929724927770624 |
|---|---|
| author | Zhang, Wenyu Luo, Jie Zhang, Xinming Fang, Yuan |
| author_facet | Zhang, Wenyu Luo, Jie Zhang, Xinming Fang, Yuan |
| contents | With the explosive growth of multimodal content online, pre-trained visual-language models have shown great potential for multimodal recommendation. However, while these models achieve decent performance when applied in a frozen manner, surprisingly, due to significant domain gaps (e.g., feature distribution discrepancy and task objective misalignment) between pre-training and personalized recommendation, adopting a joint training approach instead leads to performance worse than baseline. Existing approaches either rely on simple feature extraction or require computationally expensive full model fine-tuning, struggling to balance effectiveness and efficiency. To tackle these challenges, we propose \textbf{P}arameter-efficient \textbf{T}uning for \textbf{M}ultimodal \textbf{Rec}ommendation (\textbf{PTMRec}), a novel framework that bridges the domain gap between pre-trained models and recommendation systems through a knowledge-guided dual-stage parameter-efficient training strategy. This framework not only eliminates the need for costly additional pre-training but also flexibly accommodates various parameter-efficient tuning methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15542 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations Zhang, Wenyu Luo, Jie Zhang, Xinming Fang, Yuan Information Retrieval Artificial Intelligence With the explosive growth of multimodal content online, pre-trained visual-language models have shown great potential for multimodal recommendation. However, while these models achieve decent performance when applied in a frozen manner, surprisingly, due to significant domain gaps (e.g., feature distribution discrepancy and task objective misalignment) between pre-training and personalized recommendation, adopting a joint training approach instead leads to performance worse than baseline. Existing approaches either rely on simple feature extraction or require computationally expensive full model fine-tuning, struggling to balance effectiveness and efficiency. To tackle these challenges, we propose \textbf{P}arameter-efficient \textbf{T}uning for \textbf{M}ultimodal \textbf{Rec}ommendation (\textbf{PTMRec}), a novel framework that bridges the domain gap between pre-trained models and recommendation systems through a knowledge-guided dual-stage parameter-efficient training strategy. This framework not only eliminates the need for costly additional pre-training but also flexibly accommodates various parameter-efficient tuning methods. |
| title | Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2502.15542 |