Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Jialei, Xu, Yuanbo, Jiang, Yiheng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909623067344896
author Chen, Jialei
Xu, Yuanbo
Jiang, Yiheng
author_facet Chen, Jialei
Xu, Yuanbo
Jiang, Yiheng
contents In this paper, we focus on the often-overlooked issue of embedding collapse in existing diffusion-based sequential recommendation models and propose ADRec, an innovative framework designed to mitigate this problem. Diverging from previous diffusion-based methods, ADRec applies an independent noise process to each token and performs diffusion across the entire target sequence during training. ADRec captures token interdependency through auto-regression while modeling per-token distributions through token-level diffusion. This dual approach enables the model to effectively capture both sequence dynamics and item representations, overcoming the limitations of existing methods. To further mitigate embedding collapse, we propose a three-stage training strategy: (1) pre-training the embedding weights, (2) aligning these weights with the ADRec backbone, and (3) fine-tuning the model. During inference, ADRec applies the denoising process only to the last token, ensuring that the meaningful patterns in historical interactions are preserved. Our comprehensive empirical evaluation across six datasets underscores the effectiveness of ADRec in enhancing both the accuracy and efficiency of diffusion-based sequential recommendation systems.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach
Chen, Jialei
Xu, Yuanbo
Jiang, Yiheng
Information Retrieval
Machine Learning
In this paper, we focus on the often-overlooked issue of embedding collapse in existing diffusion-based sequential recommendation models and propose ADRec, an innovative framework designed to mitigate this problem. Diverging from previous diffusion-based methods, ADRec applies an independent noise process to each token and performs diffusion across the entire target sequence during training. ADRec captures token interdependency through auto-regression while modeling per-token distributions through token-level diffusion. This dual approach enables the model to effectively capture both sequence dynamics and item representations, overcoming the limitations of existing methods. To further mitigate embedding collapse, we propose a three-stage training strategy: (1) pre-training the embedding weights, (2) aligning these weights with the ADRec backbone, and (3) fine-tuning the model. During inference, ADRec applies the denoising process only to the last token, ensuring that the meaningful patterns in historical interactions are preserved. Our comprehensive empirical evaluation across six datasets underscores the effectiveness of ADRec in enhancing both the accuracy and efficiency of diffusion-based sequential recommendation systems.
title Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2505.19544