DReX: An Explainable Deep Learning-based Multimodal Recommendation Framework

2026-02-23

AI Summary

Existing multimodal recommendation methods often process modalities in isolation, rely on complete data, or learn user and item representations independently, leading to poor alignment, high complexity, and sensitivity to missing modalities. To address these limitations, this work proposes DReX, a novel framework featuring an interaction-driven incremental representation update mechanism. DReX dynamically integrates fine-grained multimodal interaction signals—such as ratings and reviews—via gated recurrent units (GRUs), jointly optimizing user and item representations without requiring separate feature extraction. The approach inherently handles missing modalities, simultaneously captures local interactions and global preferences, and automatically generates interpretable keyword-based profiles. Experiments on three real-world datasets demonstrate that DReX significantly outperforms state-of-the-art methods, achieving both superior recommendation performance and enhanced model transparency.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Multimodal recommender systems leverage diverse data sources, such as user interactions, content features, and contextual information, to address challenges like cold-start and data sparsity. However, existing methods often suffer from one or more key limitations: processing different modalities in isolation, requiring complete multimodal data for each interaction during training, or independent learning of user and item representations. These factors contribute to increased complexity and potential misalignment between user and item embeddings. To address these challenges, we propose DReX, a unified multimodal recommendation framework that incrementally refines user and item representations by leveraging interaction-level features from multimodal feedback. Our model employs gated recurrent units to selectively integrate these fine-grained features into global representations. This incremental update mechanism provides three key advantages: (1) simultaneous modeling of both nuanced interaction details and broader preference patterns, (2) eliminates the need for separate user and item feature extraction processes, leading to enhanced alignment in their learned representation, and (3) inherent robustness to varying or missing modalities. We evaluate the performance of the proposed approach on three real-world datasets containing reviews and ratings as interaction modalities. By considering review text as a modality, our approach automatically generates interpretable keyword profiles for both users and items, which supplement the recommendation process with interpretable preference indicators. Experiment results demonstrate that our approach outperforms state-of-the-art methods across all evaluated datasets.

Problem

• multimodal recommendation
• cold-start
• data sparsity
• embedding alignment
• missing modalities

Innovation

• multimodal recommendation
• incremental representation learning
• gated recurrent units
• explainable AI
• missing modality robustness