STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Maolin, Zhang, Sheng, Guo, Ruocheng, Wang, Wanyu, Wei, Xuetao, Liu, Zitao, Yin, Hongzhi, Chang, Yi, Zhao, Xiangyu
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866910929636032512
author	Wang, Maolin Zhang, Sheng Guo, Ruocheng Wang, Wanyu Wei, Xuetao Liu, Zitao Yin, Hongzhi Chang, Yi Zhao, Xiangyu
author_facet	Wang, Maolin Zhang, Sheng Guo, Ruocheng Wang, Wanyu Wei, Xuetao Liu, Zitao Yin, Hongzhi Chang, Yi Zhao, Xiangyu
contents	Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capturing diverse interaction patterns. We propose STAR-Rec, a novel architecture that synergistically combines preference-aware attention and state-space modeling through a sequence-level mixture-of-experts framework. STAR-Rec addresses these challenges by: (1) employing preference-aware attention to capture both inherently similar item relationships and diverse preferences, (2) utilizing state-space modeling to efficiently process variable-length sequences with linear complexity, and (3) incorporating a mixture-of-experts component that adaptively routes different behavioral patterns to specialized experts, handling both focused category-specific browsing and diverse category exploration patterns. We theoretically demonstrate how the state space model and attention mechanisms can be naturally unified in recommendation scenarios, where SSM captures temporal dynamics through state compression while attention models both similar and diverse item relationships. Extensive experiments on four real-world datasets demonstrate that STAR-Rec consistently outperforms state-of-the-art sequential recommendation methods, particularly in scenarios involving diverse user behaviors and varying sequence lengths.
format	Preprint
id	arxiv_https___arxiv_org_abs_2505_03484
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation Wang, Maolin Zhang, Sheng Guo, Ruocheng Wang, Wanyu Wei, Xuetao Liu, Zitao Yin, Hongzhi Chang, Yi Zhao, Xiangyu Information Retrieval Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capturing diverse interaction patterns. We propose STAR-Rec, a novel architecture that synergistically combines preference-aware attention and state-space modeling through a sequence-level mixture-of-experts framework. STAR-Rec addresses these challenges by: (1) employing preference-aware attention to capture both inherently similar item relationships and diverse preferences, (2) utilizing state-space modeling to efficiently process variable-length sequences with linear complexity, and (3) incorporating a mixture-of-experts component that adaptively routes different behavioral patterns to specialized experts, handling both focused category-specific browsing and diverse category exploration patterns. We theoretically demonstrate how the state space model and attention mechanisms can be naturally unified in recommendation scenarios, where SSM captures temporal dynamics through state compression while attention models both similar and diverse item relationships. Extensive experiments on four real-world datasets demonstrate that STAR-Rec consistently outperforms state-of-the-art sequential recommendation methods, particularly in scenarios involving diverse user behaviors and varying sequence lengths.
title	STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation
topic	Information Retrieval
url	https://arxiv.org/abs/2505.03484