Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Bangguo, Huo, Peng, Zhao, Yuanbo, Du, Zhicheng, Yin, Jun, Wang, Senzhang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910279610138624
author Zhu, Bangguo
Huo, Peng
Zhao, Yuanbo
Du, Zhicheng
Yin, Jun
Wang, Senzhang
author_facet Zhu, Bangguo
Huo, Peng
Zhao, Yuanbo
Du, Zhicheng
Yin, Jun
Wang, Senzhang
contents Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indices (SIDs). Owing to the exceptional generative capabilities of diffusion models, a few pioneering works explore developing GRs with diffusion architectures as the backbone. However, a fatal limitation of existing diffusion-based GRs is that the diffusion process applies uniformly to all items within the historical interactions. In contrast, the user preference is shaped by multifaceted time-evolving factors and thus exhibits a non-stationary distribution in the temporal aspect. To bridge this gap, this study proposes a novel GR framework, named TDPM, by designing the time-aware diffusion on SID tokens. Specifically, TDPM explicitly integrates the impact of time-evolving user preferences into the diffusion process. In detail, the user preference is disentangled into (i) the period preference, which remains consistent over a long time-span, and (ii) the point preference, which is triggered by recent focal events. Extensive experiments on three public real-world datasets demonstrate the significant superiority of TDPM over the state-of-the-art baselines. TDPM achieves average improvements of up to 29.21% and 25.45% in terms of HR@20 and NDCG@20, respectively. The ablation study further underscores the necessity of time-aware token diffusion in diffusion-based GRs.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01670
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
Zhu, Bangguo
Huo, Peng
Zhao, Yuanbo
Du, Zhicheng
Yin, Jun
Wang, Senzhang
Information Retrieval
Artificial Intelligence
Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indices (SIDs). Owing to the exceptional generative capabilities of diffusion models, a few pioneering works explore developing GRs with diffusion architectures as the backbone. However, a fatal limitation of existing diffusion-based GRs is that the diffusion process applies uniformly to all items within the historical interactions. In contrast, the user preference is shaped by multifaceted time-evolving factors and thus exhibits a non-stationary distribution in the temporal aspect. To bridge this gap, this study proposes a novel GR framework, named TDPM, by designing the time-aware diffusion on SID tokens. Specifically, TDPM explicitly integrates the impact of time-evolving user preferences into the diffusion process. In detail, the user preference is disentangled into (i) the period preference, which remains consistent over a long time-span, and (ii) the point preference, which is triggered by recent focal events. Extensive experiments on three public real-world datasets demonstrate the significant superiority of TDPM over the state-of-the-art baselines. TDPM achieves average improvements of up to 29.21% and 25.45% in terms of HR@20 and NDCG@20, respectively. The ablation study further underscores the necessity of time-aware token diffusion in diffusion-based GRs.
title Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2606.01670