{"ID":2855661,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12325","arxiv_id":"2510.12325","title":"Causal Inspired Multi Modal Recommendation","abstract":"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.","short_abstract":"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) simul...","url_abs":"https://arxiv.org/abs/2510.12325","url_pdf":"https://arxiv.org/pdf/2510.12325v1","authors":"[\"Jie Yang\",\"Chenyang Gu\",\"Zixuan Liu\"]","published":"2025-10-14T09:29:07Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}