Joint Similarity Item Exploration and Overlapped User Guidance for Multi-Modal Cross-Domain Recommendation

2025-02-22

AI Summary

To address the challenges of low user overlap and strong multimodal noise in multimodal cross-domain recommendation (MMCDR), which hinder effective knowledge transfer, this paper proposes a unified framework that jointly explores item-level similarity and leverages overlapping users as guidance. Methodologically, it integrates graph-structured modeling with modality-aware attention-based collaborative filtering, designs an optimal user-matching strategy, and introduces a multimodal embedding alignment mechanism to achieve intra-modal denoising and sparse cross-domain user knowledge distillation. The key innovation lies in the first joint modeling of item-level similarity exploration and overlapping-user guidance, effectively alleviating cross-domain data sparsity and multimodal interference. Extensive experiments on the Amazon multi-domain benchmark demonstrate that our approach achieves a 12.7% improvement in Recall@20 over state-of-the-art methods and significantly enhances generalization performance for non-overlapping users.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Cross-Domain Recommendation (CDR) has been widely investigated for solving long-standing data sparsity problem via knowledge sharing across domains. In this paper, we focus on the Multi-Modal Cross-Domain Recommendation (MMCDR) problem where different items have multi-modal information while few users are overlapped across domains. MMCDR is particularly challenging in two aspects: fully exploiting diverse multi-modal information within each domain and leveraging useful knowledge transfer across domains. However, previous methods fail to cluster items with similar characteristics while filtering out inherit noises within different modalities, hurdling the model performance. What is worse, conventional CDR models primarily rely on overlapped users for domain adaptation, making them ill-equipped to handle scenarios where the majority of users are non-overlapped. To fill this gap, we propose Joint Similarity Item Exploration and Overlapped User Guidance (SIEOUG) for solving the MMCDR problem. SIEOUG first proposes similarity item exploration module, which not only obtains pair-wise and group-wise item-item graph knowledge, but also reduces irrelevant noise for multi-modal modeling. Then SIEOUG proposes user-item collaborative filtering module to aggregate user/item embeddings with the attention mechanism for collaborative filtering. Finally SIEOUG proposes overlapped user guidance module with optimal user matching for knowledge sharing across domains. Our empirical study on Amazon dataset with several different tasks demonstrates that SIEOUG significantly outperforms the state-of-the-art models under the MMCDR setting.

Problem

• Multi-Modal Cross-Domain Recommendation
• Exploit multi-modal information
• Handle non-overlapped users

Innovation

• Similarity item exploration module
• User-item collaborative filtering module
• Overlapped user guidance module