Dual Conditional Diffusion Models for Sequential Recommendation

2024-10-29

arXiv.org

AI Summary

Existing implicit diffusion models for sequential recommendation compress user behavior into a single representation, discarding sequential structure and contextual information; moreover, explicit signals—such as interaction patterns—are inadequately modeled. To address this, we propose the Dual-Conditional Diffusion Transformer (DCDT), the first framework to construct a complete reverse Markov chain from discrete item indices to continuous embeddings, explicitly modeling the reverse transition process of target item indices. DCDT innovatively integrates implicit user behavioral representations with explicit sequential and interaction-based conditions, enabling dynamic, noise-robust dual-signal coordination via a conditional Transformer. Extensive experiments on multiple benchmarks demonstrate significant improvements over state-of-the-art methods: average gains of 3.2% in Recall@10 and 2.8% in NDCG@10. These results validate the effectiveness and generalizability of our discrete-to-continuous consistency modeling paradigm.

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: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Recent advancements in diffusion models have shown promising results in sequential recommendation (SR). However, current diffusion-based methods still exhibit two key limitations. First, they implicitly model the diffusion process for target item embeddings rather than the discrete target item itself, leading to inconsistency in the recommendation process. Second, existing methods rely on either implicit or explicit conditional diffusion models, limiting their ability to fully capture the context of user behavior and leading to less robust target item embeddings. In this paper, we propose the Dual Conditional Diffusion Models for Sequential Recommendation (DCRec), introducing a discrete-to-continuous sequential recommendation diffusion framework. Our framework introduces a complete Markov chain to model the transition from the reversed target item representation to the discrete item index, bridging the discrete and continuous item spaces for diffusion models and ensuring consistency with the diffusion framework. Building on this framework, we present the Dual Conditional Diffusion Transformer (DCDT) that incorporates the implicit conditional and the explicit conditional for diffusion-based SR. Extensive experiments on public benchmark datasets demonstrate that DCRec outperforms state-of-the-art methods.

Problem

• Loss of sequential and contextual information in SR
• Underutilization of explicit user-item interaction data
• Challenges in integrating implicit and explicit information

Innovation

• Dual Conditional Diffusion Models integrate implicit and explicit information
• Dual Conditional Diffusion Transformer uses cross-attention mechanism
• Model retains sequential and contextual information for precise recommendations