# Disentangled Multimodal Representation Learning for Recommendation

arXiv: https://arxiv.org/abs/2203.05406 · HTML: https://mlsanity.com/paper/2203.05406/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2022.

## Built on by (most cited first, 15 of 15)

- [Multimodal Recommender Systems: A Survey](https://mlsanity.com/paper/2302.03883/) (2023)
- [On the Embedding Collapse when Scaling up Recommendation Models](https://mlsanity.com/paper/2310.04400/) (2023)
- [DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning](https://mlsanity.com/paper/2503.11892/) (2025)
- [Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction](https://mlsanity.com/paper/2403.10883/) (2024)
- [Modality-Balanced Learning for Multimedia Recommendation](https://mlsanity.com/paper/2408.06360/) (2024)
- [Dual Semantic Knowledge Composed Multimodal Dialog Systems](https://mlsanity.com/paper/2305.09990/) (2023)
- [Dynamic Evidence Decoupling for Trusted Multi-view Learning](https://mlsanity.com/paper/2410.03796/) (2024)
- [Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video Recommendation](https://mlsanity.com/paper/2501.07110/) (2025)
- [BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance](https://mlsanity.com/paper/2506.03589/) (2025)
- [ATR-UMMIM: A Benchmark Dataset for UAV-Based Multimodal Image Registration under Complex Imaging Conditions](https://mlsanity.com/paper/2507.20764/) (2025)
- [Multi-QuAD: Multi-Level Quality-Adaptive Dynamic Network for Reliable Multimodal Classification](https://mlsanity.com/paper/2412.14489/) (2024)
- [Feature Fusion Revisited: Multimodal CTR Prediction for MMCTR Challenge](https://mlsanity.com/paper/2504.18961/) (2025)
- [A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2508.19620/) (2025)
- [Multimodal Representation-disentangled Information Bottleneck for Multimodal Recommendation](https://mlsanity.com/paper/2509.20225/) (2025)
- [Modality-Guided Mixture of Structured Experts with Entropy-Triggered Routing for Multimodal Recommendation](https://mlsanity.com/paper/2602.20723/) (2026)

## Abstract (arXiv)

Many multimodal recommender systems have been proposed to exploit the rich side information associated with users or items (e.g., user reviews and item images) for learning better user and item representations to improve the recommendation performance. Studies from psychology show that users have individual differences in the utilization of various modalities for organizing information. Therefore, for a certain factor of an item (such as appearance or quality), the features of different modalities are of varying importance to a user. However, existing methods ignore the fact that different modalities contribute differently towards a user's preference on various factors of an item. In light of this, in this paper, we propose a novel Disentangled Multimodal Representation Learning (DMRL) recommendation model, which can capture users' attention to different modalities on each factor in user preference modeling. In particular, we employ a disentangled representation technique to ensure the features of different factors in each modality are independent of each other. A multimodal attention mechanism is then designed to capture users' modality preference for each factor. Based on the estimated weights obtained by the attention mechanism, we make recommendations by combining the preference scores of a user's preferences to each factor of the target item over different modalities. Extensive evaluation on five real-world datasets demonstrate the superiority of our method compared with existing methods.