Gated Multimodal Graph Learning for Personalized Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912405397700608 |
|---|---|
| author | Liu, Sibei Zhang, Yuanzhe Li, Xiang Liu, Yunbo Feng, Chengwei Yang, Hao |
| author_facet | Liu, Sibei Zhang, Yuanzhe Li, Xiang Liu, Yunbo Feng, Chengwei Yang, Hao |
| contents | Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering by incorporating rich content information, such as product images and textual descriptions. However, effectively integrating heterogeneous modalities into a unified recommendation framework remains a challenge. Existing approaches often rely on fixed fusion strategies or complex architectures , which may fail to adapt to modality quality variance or introduce unnecessary computational overhead.
In this work, we propose RLMultimodalRec, a lightweight and modular recommendation framework that combines graph-based user modeling with adaptive multimodal item encoding. The model employs a gated fusion module to dynamically balance the contribution of visual and textual modalities, enabling fine-grained and content-aware item representations. Meanwhile, a two-layer LightGCN encoder captures high-order collaborative signals by propagating embeddings over the user-item interaction graph without relying on nonlinear transformations.
We evaluate our model on a real-world dataset from the Amazon product domain. Experimental results demonstrate that RLMultimodalRec consistently outperforms several competitive baselines, including collaborative filtering, visual-aware, and multimodal GNN-based methods. The proposed approach achieves significant improvements in top-K recommendation metrics while maintaining scalability and interpretability, making it suitable for practical deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00107 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gated Multimodal Graph Learning for Personalized Recommendation Liu, Sibei Zhang, Yuanzhe Li, Xiang Liu, Yunbo Feng, Chengwei Yang, Hao Information Retrieval Artificial Intelligence Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering by incorporating rich content information, such as product images and textual descriptions. However, effectively integrating heterogeneous modalities into a unified recommendation framework remains a challenge. Existing approaches often rely on fixed fusion strategies or complex architectures , which may fail to adapt to modality quality variance or introduce unnecessary computational overhead. In this work, we propose RLMultimodalRec, a lightweight and modular recommendation framework that combines graph-based user modeling with adaptive multimodal item encoding. The model employs a gated fusion module to dynamically balance the contribution of visual and textual modalities, enabling fine-grained and content-aware item representations. Meanwhile, a two-layer LightGCN encoder captures high-order collaborative signals by propagating embeddings over the user-item interaction graph without relying on nonlinear transformations. We evaluate our model on a real-world dataset from the Amazon product domain. Experimental results demonstrate that RLMultimodalRec consistently outperforms several competitive baselines, including collaborative filtering, visual-aware, and multimodal GNN-based methods. The proposed approach achieves significant improvements in top-K recommendation metrics while maintaining scalability and interpretability, making it suitable for practical deployment. |
| title | Gated Multimodal Graph Learning for Personalized Recommendation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2506.00107 |