Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jiyuan, Li, Yuanzi, Zhao, Jingyu, Wang, Hanbing, Ma, Muyang, Ma, Jun, Ren, Zhaochun, Zhang, Mengqi, Xin, Xin, Chen, Zhumin, Ren, Pengjie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914727741882368
author Yang, Jiyuan
Li, Yuanzi
Zhao, Jingyu
Wang, Hanbing
Ma, Muyang
Ma, Jun
Ren, Zhaochun
Zhang, Mengqi
Xin, Xin
Chen, Zhumin
Ren, Pengjie
author_facet Yang, Jiyuan
Li, Yuanzi
Zhao, Jingyu
Wang, Hanbing
Ma, Muyang
Ma, Jun
Ren, Zhaochun
Zhang, Mengqi
Xin, Xin
Chen, Zhumin
Ren, Pengjie
contents Sequential Recommenders have been widely applied in various online services, aiming to model users' dynamic interests from their sequential interactions. With users increasingly engaging with online platforms, vast amounts of lifelong user behavioral sequences have been generated. However, existing sequential recommender models often struggle to handle such lifelong sequences. The primary challenges stem from computational complexity and the ability to capture long-range dependencies within the sequence. Recently, a state space model featuring a selective mechanism (i.e., Mamba) has emerged. In this work, we investigate the performance of Mamba for lifelong sequential recommendation (i.e., length>=2k). More specifically, we leverage the Mamba block to model lifelong user sequences selectively. We conduct extensive experiments to evaluate the performance of representative sequential recommendation models in the setting of lifelong sequences. Experiments on two real-world datasets demonstrate the superiority of Mamba. We found that RecMamba achieves performance comparable to the representative model while significantly reducing training duration by approximately 70% and memory costs by 80%. Codes and data are available at \url{https://github.com/nancheng58/RecMamba}.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16371
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation
Yang, Jiyuan
Li, Yuanzi
Zhao, Jingyu
Wang, Hanbing
Ma, Muyang
Ma, Jun
Ren, Zhaochun
Zhang, Mengqi
Xin, Xin
Chen, Zhumin
Ren, Pengjie
Information Retrieval
Sequential Recommenders have been widely applied in various online services, aiming to model users' dynamic interests from their sequential interactions. With users increasingly engaging with online platforms, vast amounts of lifelong user behavioral sequences have been generated. However, existing sequential recommender models often struggle to handle such lifelong sequences. The primary challenges stem from computational complexity and the ability to capture long-range dependencies within the sequence. Recently, a state space model featuring a selective mechanism (i.e., Mamba) has emerged. In this work, we investigate the performance of Mamba for lifelong sequential recommendation (i.e., length>=2k). More specifically, we leverage the Mamba block to model lifelong user sequences selectively. We conduct extensive experiments to evaluate the performance of representative sequential recommendation models in the setting of lifelong sequences. Experiments on two real-world datasets demonstrate the superiority of Mamba. We found that RecMamba achieves performance comparable to the representative model while significantly reducing training duration by approximately 70% and memory costs by 80%. Codes and data are available at \url{https://github.com/nancheng58/RecMamba}.
title Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2403.16371