I Know Why You Like This Movie: Interpretable Efficient Multimodal Recommender

Abstract

Recently, the Efficient Manifold Density Estimator (EMDE) model has been introduced. The model exploits Local Sensitive Hashing and Count-Min Sketch algorithms, combining them with a neural network to achieve state-of-the-art results on multiple recommender datasets. However, this model ingests a compressed joint representation of all input items for each user/session, so calculating attributions for separate items via gradient-based methods seems not applicable. We prove that interpreting this model in a white-box setting is possible thanks to the properties of EMDE item retrieval method. By exploiting multimodal flexibility of this model, we obtain meaningful results showing the influence of multiple modalities: text, categorical features, and images, on movie recommendation output.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrychalska2020i

Related papers

• End-to-end Training Of Multimodal Model And Ranking Model (2024)0.00
• E-MMKGR: A Unified Multimodal Knowledge Graph Framework For E-commerce Applications (2026)0.00
• T-EMDE: Sketching-based Global Similarity For Cross-modal Retrieval (2021)0.00
• Vlm4rec: Multimodal Semantic Representation For Recommendation With Large Vision-language Models (2026)1.82
• Learning Similarity Preserving Binary Codes For Recommender Systems (2022)0.00
• Self-supervised Multi-modal Sequential Recommendation (2023)0.00
• Everyone's Preference Changes Differently: Weighted Multi-interest Retrieval Model (2022)0.00
• Domain-adaptive And Scalable Dense Retrieval For Content-based Recommendation (2026)0.00