Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users

2026-04-28

AI Summary

This work addresses the performance degradation in cross-domain recommendation for cold-start users caused by sparse interactions in the target domain, as well as the limitation of existing methods in simultaneously capturing personalized multi-interests and shared group preferences. To this end, the authors propose the NF-NPCDR framework, which innovatively integrates normalizing flows into neural processes to model multimodal personalized interest distributions. The framework further introduces a preference pool to explicitly capture commonalities across users and employs a stochastic adaptive decoder to dynamically fuse individualized and collective preferences. Extensive experiments on multiple real-world datasets demonstrate that NF-NPCDR significantly outperforms state-of-the-art cross-domain recommendation models, effectively enhancing both accuracy and diversity of recommendations for cold-start users.

Abstract

Cross-domain recommendation (CDR) has demonstrated to be an effective solution for alleviating the user cold-start issue. By leveraging rich user-item interactions available in a richly informative source domain, CDR could improve the recommendation performance for cold-start users in the target domain. Previous CDR approaches mostly adhere the Embedding and Mapping (EMCDR) paradigm, which learns a user-shared mapping function to transfer users' preference from the source domain to the target domain, neglecting users' personalized preference. Recent CDR approaches further leverage the meta-learning paradigm, considering the CDR task for each user independently and learning user-specific mapping functions for each user. However, they mostly learn representations for each user individually, which ignores the common preference between different users, neglecting valuable information for CDR. In addition, all these approaches usually summarize the user's preference into an overall representation, which can hardly capture the user's multi-interest preference. To this end, we propose a personalized multi-interest modeling framework for CDR to cold-start users, termed as NF-NPCDR. Specifically, we propose a personalized preference encoder that enhances the neural process (NP) with the normalizing flow (NF) to convert the Gaussian (unimodal) distribution to a multimodal distribution, providing a novel way to capture the user's personalized multi-interest preference. Then, we propose a common preference encoder with a preference pool to capture the common preference between different users. Furthermore, we introduce a stochastic adaptive decoder to incorporate both the personalized and common preference for cold-start users, adaptively modulating both preference for better recommendation.

Problem

• cross-domain recommendation
• cold-start users
• personalized preference
• multi-interest modeling
• common preference

Innovation

• Personalized Multi-Interest Modeling
• Cross-Domain Recommendation
• Neural Process
• Normalizing Flow
• Cold-Start Users