S2CDR: Smoothing-Sharpening Process Model for Cross-Domain Recommendation

2026-03-03

AI Summary

This work addresses the user cold-start problem in cross-domain recommendation, where existing methods struggle to effectively transfer preferences and often neglect inter-domain item relationships. The authors propose S2CDR, a novel framework that introduces a noise-free smooth-sharpen architecture to replace conventional diffusion mechanisms, modeling the recovery of unknown interactions for cold-start users via ordinary differential equations (ODEs). In the smoothing phase, cross-domain information is fused through a heat equation defined on an item similarity graph; in the sharpening phase, user preferences are iteratively reconstructed. Grounded in graph signal processing theory, a low-pass filter is designed to preserve intrinsic user preferences while explicitly modeling cross-domain item associations. Evaluated on three real-world cross-domain scenarios, S2CDR significantly outperforms state-of-the-art methods and enables efficient deployment without requiring training.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

User cold-start problem is a long-standing challenge in recommendation systems. Fortunately, cross-domain recommendation (CDR) has emerged as a highly effective remedy for the user cold-start challenge, with recently developed diffusion models (DMs) demonstrating exceptional performance. However, these DMs-based CDR methods focus on dealing with user-item interactions, overlooking correlations between items across the source and target domains. Meanwhile, the Gaussian noise added in the forward process of diffusion models would hurt user's personalized preference, leading to the difficulty in transferring user preference across domains. To this end, we propose a novel paradigm of Smoothing-Sharpening Process Model for CDR to cold-start users, termed as S2CDR which features a corruption-recovery architecture and is solved with respect to ordinary differential equations (ODEs). Specifically, the smoothing process gradually corrupts the original user-item/item-item interaction matrices derived from both domains into smoothed preference signals in a noise-free manner, and the sharpening process iteratively sharpens the preference signals to recover the unknown interactions for cold-start users. Wherein, for the smoothing process, we introduce the heat equation on the item-item similarity graph to better capture the correlations between items across domains, and further build the tailor-designed low-pass filter to filter out the high-frequency noise information for capturing user's intrinsic preference, in accordance with the graph signal processing (GSP) theory. Extensive experiments on three real-world CDR scenarios confirm that our S2CDR significantly outperforms previous SOTA methods in a training-free manner.

Problem

• cross-domain recommendation
• user cold-start
• diffusion models
• item correlation
• personalized preference

Innovation

• Cross-Domain Recommendation
• Smoothing-Sharpening Process
• Graph Signal Processing
• User Cold-Start
• Ordinary Differential Equations