Efficient Sequential Recommendation for Long Term User Interest Via Personalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Qiang, Yu, Hanchao, Ji, Ivan, Yuan, Chen, Zhang, Yi, Liu, Chihuang, Wang, Xiaolong, Lambert, Christopher E., Chen, Ren, Kovacs, Chen, Bei, Xinzhu, Cai, Renqin, Li, Rui, Zhang, Lizhu, Fan, Xiangjun, Zhang, Qunshu, Zhang, Benyu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914237984538624
author Zhang, Qiang
Yu, Hanchao
Ji, Ivan
Yuan, Chen
Zhang, Yi
Liu, Chihuang
Wang, Xiaolong
Lambert, Christopher E.
Chen, Ren
Kovacs, Chen
Bei, Xinzhu
Cai, Renqin
Li, Rui
Zhang, Lizhu
Fan, Xiangjun
Zhang, Qunshu
Zhang, Benyu
author_facet Zhang, Qiang
Yu, Hanchao
Ji, Ivan
Yuan, Chen
Zhang, Yi
Liu, Chihuang
Wang, Xiaolong
Lambert, Christopher E.
Chen, Ren
Kovacs, Chen
Bei, Xinzhu
Cai, Renqin
Li, Rui
Zhang, Lizhu
Fan, Xiangjun
Zhang, Qunshu
Zhang, Benyu
contents Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at \href{https://github.com/facebookresearch/PerSRec}{https://github.com/facebookresearch/PerSRec}.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03479
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Sequential Recommendation for Long Term User Interest Via Personalization
Zhang, Qiang
Yu, Hanchao
Ji, Ivan
Yuan, Chen
Zhang, Yi
Liu, Chihuang
Wang, Xiaolong
Lambert, Christopher E.
Chen, Ren
Kovacs, Chen
Bei, Xinzhu
Cai, Renqin
Li, Rui
Zhang, Lizhu
Fan, Xiangjun
Zhang, Qunshu
Zhang, Benyu
Information Retrieval
Artificial Intelligence
Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at \href{https://github.com/facebookresearch/PerSRec}{https://github.com/facebookresearch/PerSRec}.
title Efficient Sequential Recommendation for Long Term User Interest Via Personalization
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2601.03479