Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Qijiong, Fan, Lu, Liu, Zhongzhou, Dong, Xiaoyu, Luo, Yuankai, An, Guoyuan, Chen, Nuo, Guo, Wei, Liu, Yong, Wu, Xiao-Ming
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.19158
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917224993783808
author Liu, Qijiong
Fan, Lu
Liu, Zhongzhou
Dong, Xiaoyu
Luo, Yuankai
An, Guoyuan
Chen, Nuo
Guo, Wei
Liu, Yong
Wu, Xiao-Ming
author_facet Liu, Qijiong
Fan, Lu
Liu, Zhongzhou
Dong, Xiaoyu
Luo, Yuankai
An, Guoyuan
Chen, Nuo
Guo, Wei
Liu, Yong
Wu, Xiao-Ming
contents Although generative recommenders demonstrate improved performance with longer sequences, their real-time deployment is hindered by substantial computational costs. To address this challenge, we propose a simple yet effective method for compressing long-term user histories by leveraging inherent item categorical features, thereby preserving user interests while enhancing efficiency. Experiments on two large-scale datasets demonstrate that, compared to the influential HSTU model, our approach achieves up to a 6x reduction in computational cost and up to 39% higher accuracy at comparable cost (i.e., similar sequence length).
format Preprint
id arxiv_https___arxiv_org_abs_2601_19158
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Accelerating Generative Recommendation via Simple Categorical User Sequence Compression
Liu, Qijiong
Fan, Lu
Liu, Zhongzhou
Dong, Xiaoyu
Luo, Yuankai
An, Guoyuan
Chen, Nuo
Guo, Wei
Liu, Yong
Wu, Xiao-Ming
Information Retrieval
Although generative recommenders demonstrate improved performance with longer sequences, their real-time deployment is hindered by substantial computational costs. To address this challenge, we propose a simple yet effective method for compressing long-term user histories by leveraging inherent item categorical features, thereby preserving user interests while enhancing efficiency. Experiments on two large-scale datasets demonstrate that, compared to the influential HSTU model, our approach achieves up to a 6x reduction in computational cost and up to 39% higher accuracy at comparable cost (i.e., similar sequence length).
title Accelerating Generative Recommendation via Simple Categorical User Sequence Compression
topic Information Retrieval
url https://arxiv.org/abs/2601.19158