Unconditional Diffusion for Generative Sequential Recommendation

2025-07-08

AI Summary

Existing conditional diffusion models for sequential recommendation weaken user history utilization by modeling the “item ↔ noise” transformation, treating historical sequences as auxiliary conditions rather than central structural anchors. Method: We propose an unconditional Brownian bridge diffusion model that designates the user’s historical behavior sequence as the deterministic terminal point of the diffusion process—rather than a conditional input—thereby focusing exclusively on modeling the evolutionary relationships among items. By constructing bidirectional Brownian bridge paths anchored at the observed history, we jointly constrain noise injection and denoising, eliminating interference from conventional conditional modeling. The model employs an end-to-end denoising architecture to directly generate personalized sequences from pure noise. Contribution/Results: Our approach achieves significant improvements over state-of-the-art methods across multiple public benchmarks, empirically validating the efficacy of history-centric diffusion modeling. The implementation is publicly available.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• 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

Diffusion models, known for their generative ability to simulate data creation through noise-adding and denoising processes, have emerged as a promising approach for building generative recommenders. To incorporate user history for personalization, existing methods typically adopt a conditional diffusion framework, where the reverse denoising process of reconstructing items from noise is modified to be conditioned on the user history. However, this design may fail to fully utilize historical information, as it gets distracted by the need to model the "item $leftrightarrow$ noise" translation. This motivates us to reformulate the diffusion process for sequential recommendation in an unconditional manner, treating user history (instead of noise) as the endpoint of the forward diffusion process (i.e., the starting point of the reverse process), rather than as a conditional input. This formulation allows for exclusive focus on modeling the "item $leftrightarrow$ history" translation. To this end, we introduce Brownian Bridge Diffusion Recommendation (BBDRec). By leveraging a Brownian bridge process, BBDRec enforces a structured noise addition and denoising mechanism, ensuring that the trajectories are constrained towards a specific endpoint -- user history, rather than noise. Extensive experiments demonstrate BBDRec's effectiveness in enhancing sequential recommendation performance. The source code is available at https://github.com/baiyimeng/BBDRec.

Problem

• Reformulate diffusion process for sequential recommendation unconditionally
• Enhance user history utilization in generative recommenders
• Improve item-history translation modeling via Brownian bridge

Innovation

• Unconditional diffusion process using user history
• Brownian bridge for structured noise addition
• Focus on item-history translation exclusively