Align-for-Fusion: Harmonizing Triple Preferences via Dual-oriented Diffusion for Cross-domain Sequential Recommendation

2025-08-07

AI Summary

To address data sparsity, interest drift, and coarse-grained domain preference modeling—stemming from the prevalent “align-then-fuse” paradigm in cross-domain sequential recommendation (CDSR)—this paper proposes Align-for-Fusion, a novel framework centered on a dual-perspective diffusion model. It jointly models user behaviors across three domains to enable fine-grained, multi-source preference fusion. We introduce a hybrid conditional distribution retrieval strategy that leverages users’ authentic behavioral logic as a cross-domain semantic bridge, and design a bi-directional preference diffusion mechanism to simultaneously suppress noise and enhance target-relevant interests. By integrating diffusion-driven distribution matching, uncertainty-aware alignment, and fusion, our method achieves significant improvements over state-of-the-art approaches on four CDSR benchmarks, demonstrating both effectiveness and robustness.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Application Domains: Humanities & Computational Social Science
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

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

Personalized sequential recommendation aims to predict appropriate items for users based on their behavioral sequences. To alleviate data sparsity and interest drift issues, conventional approaches typically incorporate auxiliary behaviors from other domains via cross-domain transition. However, existing cross-domain sequential recommendation (CDSR) methods often follow an align-then-fusion paradigm that performs representation-level alignment across multiple domains and combines them mechanically for recommendation, overlooking the fine-grained fusion of domain-specific preferences. Inspired by recent advances in diffusion models (DMs) for distribution matching, we propose an align-for-fusion framework for CDSR to harmonize triple preferences via dual-oriented DMs, termed HorizonRec. Specifically, we investigate the uncertainty injection of DMs and identify stochastic noise as a key source of instability in existing DM-based recommenders. To address this, we introduce a mixed-conditioned distribution retrieval strategy that leverages distributions retrieved from users' authentic behavioral logic as semantic bridges across domains, enabling consistent multi-domain preference modeling. Furthermore, we propose a dual-oriented preference diffusion method to suppress potential noise and emphasize target-relevant interests during multi-domain user representation fusion. Extensive experiments on four CDSR datasets from two distinct platforms demonstrate the effectiveness and robustness of HorizonRec in fine-grained triple-domain preference fusion.

Problem

• Harmonizing triple preferences in cross-domain sequential recommendation
• Addressing instability in diffusion model-based recommenders
• Enhancing fine-grained multi-domain preference fusion

Innovation

• Align-for-fusion framework harmonizes triple preferences
• Mixed-conditioned distribution retrieval strategy reduces noise
• Dual-oriented preference diffusion suppresses noise effectively