Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback

TL;DR

This paper introduces DA-MRS, a novel multi-modal recommender system that effectively denoises content and user feedback while aligning multi-modal data to improve recommendation accuracy.

Contribution

The paper proposes a comprehensive framework that addresses noise and alignment issues in multi-modal recommender systems, enhancing their robustness and effectiveness.

Findings

DA-MRS outperforms baseline models across multiple datasets.

The framework effectively denoises user feedback and content.

Alignment strategies improve recommendation precision.

Abstract

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.