Exploring Preference-Guided Diffusion Model for Cross-Domain Recommendation

2025-01-20

AI Summary

To address the cold-start problem in cross-domain recommendation—specifically, how to achieve accurate recommendations when the target domain lacks user interaction data—this paper proposes DMCDR, a preference-guided diffusion model. DMCDR is the first to introduce diffusion models into cross-domain recommendation: it constructs fine-grained user preference signals from source-domain interaction history and dynamically injects these signals into the conditional denoising process, enabling progressive preference transfer to the target domain. Innovatively, it designs a dedicated preference encoder and a conditional diffusion mechanism, overcoming the coarse-grained representation limitations of conventional embedding-mapping paradigms. Extensive experiments on multiple cross-domain benchmark datasets demonstrate that DMCDR significantly improves recommendation performance for cold-start users in the target domain. A systematic ablation study validates the effectiveness of six diffusion variants. This work establishes a novel paradigm for applying diffusion models to transfer-based recommendation.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Recommender Systems
• Computer Vision: Diffusion Models for Vision

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Cross-domain recommendation (CDR) has been proven as a promising way to alleviate the cold-start issue, in which the most critical problem is how to draw an informative user representation in the target domain via the transfer of user preference existing in the source domain. Prior efforts mostly follow the embedding-and-mapping paradigm, which first integrate the preference into user representation in the source domain, and then perform a mapping function on this representation to the target domain. However, they focus on mapping features across domains, neglecting to explicitly model the preference integration process, which may lead to learning coarse user representation. Diffusion models (DMs), which contribute to more accurate user/item representations due to their explicit information injection capability, have achieved promising performance in recommendation systems. Nevertheless, these DMs-based methods cannot directly account for valuable user preference in other domains, leading to challenges in adapting to the transfer of preference for cold-start users. Consequently, the feasibility of DMs for CDR remains underexplored. To this end, we explore to utilize the explicit information injection capability of DMs for user preference integration and propose a Preference-Guided Diffusion Model for CDR to cold-start users, termed as DMCDR. Specifically, we leverage a preference encoder to establish the preference guidance signal with the user's interaction history in the source domain. Then, we explicitly inject the preference guidance signal into the user representation step by step to guide the reverse process, and ultimately generate the personalized user representation in the target domain, thus achieving the transfer of user preference across domains. Furthermore, we comprehensively explore the impact of six DMs-based variants on CDR.

Problem

• Cross-domain Recommendation
• Cold Start Problem
• User Behavior Analysis

Innovation

• DMCDR Model
• Cross-domain Recommendation
• Cold-start Problem