Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback
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_ | 1866910901117911040 |
|---|---|
| author | Xv, Guipeng Li, Xinyu Xie, Ruobing Lin, Chen Liu, Chong Xia, Feng Kang, Zhanhui Lin, Leyu |
| author_facet | Xv, Guipeng Li, Xinyu Xie, Ruobing Lin, Chen Liu, Chong Xia, Feng Kang, Zhanhui Lin, Leyu |
| contents | Multi-modal recommender systems (MRSs) are pivotal in diverse online web platforms and have garnered considerable attention in recent years. However, previous studies overlook the challenges of (1) noisy multi-modal content, (2) noisy user feedback, and (3) aligning multi-modal content with user feedback. In order to tackle these challenges, we propose Denoising and Aligning Multi-modal Recommender System (DA-MRS). To mitigate multi-modal noise, DA-MRS first constructs item-item graphs determined by consistent content similarity across modalities. To denoise user feedback, DA-MRS associates the probability of observed feedback with multi-modal content and devises a denoised BPR loss. Furthermore, DA-MRS implements Alignment guided by User preference to enhance task-specific item representation and Alignment guided by graded Item relations to provide finer-grained alignment. Extensive experiments verify that DA-MRS is a plug-and-play framework and achieves significant and consistent improvements across various datasets, backbone models, and noisy scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12501 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback Xv, Guipeng Li, Xinyu Xie, Ruobing Lin, Chen Liu, Chong Xia, Feng Kang, Zhanhui Lin, Leyu Information Retrieval Multi-modal recommender systems (MRSs) are pivotal in diverse online web platforms and have garnered considerable attention in recent years. However, previous studies overlook the challenges of (1) noisy multi-modal content, (2) noisy user feedback, and (3) aligning multi-modal content with user feedback. In order to tackle these challenges, we propose Denoising and Aligning Multi-modal Recommender System (DA-MRS). To mitigate multi-modal noise, DA-MRS first constructs item-item graphs determined by consistent content similarity across modalities. To denoise user feedback, DA-MRS associates the probability of observed feedback with multi-modal content and devises a denoised BPR loss. Furthermore, DA-MRS implements Alignment guided by User preference to enhance task-specific item representation and Alignment guided by graded Item relations to provide finer-grained alignment. Extensive experiments verify that DA-MRS is a plug-and-play framework and achieves significant and consistent improvements across various datasets, backbone models, and noisy scenarios. |
| title | Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2406.12501 |