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.
@article{arxiv.2406.12501,
title = {Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback},
author = {Guipeng Xv and Xinyu Li and Ruobing Xie and Chen Lin and Chong Liu and Feng Xia and Zhanhui Kang and Leyu Lin},
journal= {arXiv preprint arXiv:2406.12501},
year = {2025}
}
Comments
After further review, we believe the content of the paper is not yet fully ready and requires additional time for improvement. To ensure quality, we have decided to withdraw this preprint