Continuous-time Discrete-space Diffusion Model for Recommendation

2025-11-15

AI Summary

Existing diffusion-based recommender systems model user historical interactions in continuous graph-encoded embedding spaces, leading to information loss and high computational overhead. To address these limitations, we propose CDRec—a continuous-time, discrete-space diffusion recommendation framework that directly defines diffusion processes over discrete interaction sequences, thereby precisely capturing the dynamic evolution of user preferences. Our key contributions include: (1) a continuous-time adaptive discrete diffusion mechanism; (2) a popularity-aware noise scheduling strategy; and (3) a joint optimization paradigm integrating consistency parameterization with multi-hop collaborative contrastive learning. By bypassing graph encoding and continuous-space projection, CDRec significantly enhances semantic representation fidelity and personalization accuracy. Extensive experiments on multiple real-world datasets demonstrate that CDRec consistently outperforms state-of-the-art methods in both recommendation accuracy and inference efficiency.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Diffusion Models for Vision

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In the era of information explosion, Recommender Systems (RS) are essential for alleviating information overload and providing personalized user experiences. Recent advances in diffusion-based generative recommenders have shown promise in capturing the dynamic nature of user preferences. These approaches explore a broader range of user interests by progressively perturbing the distribution of user-item interactions and recovering potential preferences from noise, enabling nuanced behavioral understanding. However, existing diffusion-based approaches predominantly operate in continuous space through encoded graph-based historical interactions, which may compromise potential information loss and suffer from computational inefficiency. As such, we propose CDRec, a novel Continuous-time Discrete-space Diffusion Recommendation framework, which models user behavior patterns through discrete diffusion on historical interactions over continuous time. The discrete diffusion algorithm operates via discrete element operations (e.g., masking) while incorporating domain knowledge through transition matrices, producing more meaningful diffusion trajectories. Furthermore, the continuous-time formulation enables flexible adaptive sampling. To better adapt discrete diffusion models to recommendations, CDRec introduces: (1) a novel popularity-aware noise schedule that generates semantically meaningful diffusion trajectories, and (2) an efficient training framework combining consistency parameterization for fast sampling and a contrastive learning objective guided by multi-hop collaborative signals for personalized recommendation. Extensive experiments on real-world datasets demonstrate CDRec's superior performance in both recommendation accuracy and computational efficiency.

Problem

• Modeling user preferences through discrete diffusion in continuous time
• Addressing information loss and inefficiency in graph-based diffusion models
• Developing adaptive sampling and training for personalized recommendations

Innovation

• Continuous-time discrete-space diffusion for user behavior modeling
• Popularity-aware noise schedule for meaningful diffusion trajectories
• Consistency parameterization and contrastive learning for efficient training