Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.12325 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909844599996416 |
|---|---|
| author | Yang, Jie Gu, Chenyang Liu, Zixuan |
| author_facet | Yang, Jie Gu, Chenyang Liu, Zixuan |
| contents | Multimodal recommender systems enhance personalized recommendations in e-commerce and online advertising by integrating visual, textual, and user-item interaction data. However, existing methods often overlook two critical biases: (i) modal confounding, where latent factors (e.g., brand style or product category) simultaneously drive multiple modalities and influence user preference, leading to spurious feature-preference associations; (ii) interaction bias, where genuine user preferences are mixed with noise from exposure effects and accidental clicks. To address these challenges, we propose a Causal-inspired multimodal Recommendation framework. Specifically, we introduce a dual-channel cross-modal diffusion module to identify hidden modal confounders, utilize back-door adjustment with hierarchical matching and vector-quantized codebooks to block confounding paths, and apply front-door adjustment combined with causal topology reconstruction to build a deconfounded causal subgraph. Extensive experiments on three real-world e-commerce datasets demonstrate that our method significantly outperforms state-of-the-art baselines while maintaining strong interpretability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12325 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Causal Inspired Multi Modal Recommendation Yang, Jie Gu, Chenyang Liu, Zixuan Information Retrieval Artificial Intelligence Multimodal recommender systems enhance personalized recommendations in e-commerce and online advertising by integrating visual, textual, and user-item interaction data. However, existing methods often overlook two critical biases: (i) modal confounding, where latent factors (e.g., brand style or product category) simultaneously drive multiple modalities and influence user preference, leading to spurious feature-preference associations; (ii) interaction bias, where genuine user preferences are mixed with noise from exposure effects and accidental clicks. To address these challenges, we propose a Causal-inspired multimodal Recommendation framework. Specifically, we introduce a dual-channel cross-modal diffusion module to identify hidden modal confounders, utilize back-door adjustment with hierarchical matching and vector-quantized codebooks to block confounding paths, and apply front-door adjustment combined with causal topology reconstruction to build a deconfounded causal subgraph. Extensive experiments on three real-world e-commerce datasets demonstrate that our method significantly outperforms state-of-the-art baselines while maintaining strong interpretability. |
| title | Causal Inspired Multi Modal Recommendation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2510.12325 |