arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.01192cs.IR
收藏

SSD4Rec:一种用于高效序列推荐的结构化状态空间对偶模型

SSD4Rec: A Structured State Space Duality Model for Efficient Sequential Recommendation

Haohao Qu, Yifeng Zhang, Liangbo Ning, Wenqi Fan, Qing Li

AI总结:

针对现有序列推荐方法难以高效建模长用户行为序列的问题,提出基于Mamba的SSD4Rec骨干模型,通过序列寄存器与双向SSD模块实现高效长序列建模,在四个基准上取得SOTA性能且具备近线性可扩展性。

摘要:

序列推荐方法因能基于历史交互理解用户不断变化的兴趣,在现代推荐系统中至关重要。然而,当前方法(如基于RNN或Transformer的模型)面临的一大挑战是:如何通过建模长行为序列有效且高效地捕捉用户偏好,这限制了它们在短视频平台这类用户交互量极大的场景中的各类应用。近期,一种名为Mamba的新兴架构基于状态空间模型(SSM)构建,采用高效的硬件感知设计,在序列建模方面展现出巨大潜力,为有效解决上述挑战提供了极具吸引力的方向。受此启发,我们提出了一种新型通用高效的序列推荐骨干网络SSD4Rec,探索将Mamba无缝适配于序列推荐任务。具体而言,SSD4Rec使用序列寄存器标记可变长度且较长的物品序列,并通过双向结构化状态空间对偶(SSD)模块处理物品表示。这不仅支持硬件感知的矩阵乘法,还赋予模型出色的可变长度与长程序列建模能力。在四个基准数据集上的大量评估表明,所提模型达到了当前最优性能,同时随用户序列长度呈现近线性的可扩展性。我们的代码已公开在https://github.com/ZhangYifeng1995/SSD4Rec。

英文摘要:

Sequential recommendation methods are crucial in modern recommender systems for their remarkable capability to understand a user's changing interests based on past interactions. However, a significant challenge faced by current methods (e.g., RNN- or Transformer-based models) is to effectively and efficiently capture users' preferences by modeling long behavior sequences, which impedes their various applications like short video platforms where user interactions are numerous. Recently, an emerging architecture named Mamba, built on state space models (SSM) with efficient hardware-aware designs, has showcased the tremendous potential for sequence modeling, presenting a compelling avenue for addressing the challenge effectively. Inspired by this, we propose a novel generic and efficient sequential recommendation backbone, SSD4Rec, which explores the seamless adaptation of Mamba for sequential recommendations. Specifically, SSD4Rec marks the variable- and long-length item sequences with sequence registers and processes the item representations with bidirectional Structured State Space Duality (SSD) blocks. This not only allows for hardware-aware matrix multiplication but also empowers outstanding capabilities in variable-length and long-range sequence modeling. Extensive evaluations on four benchmark datasets demonstrate that the proposed model achieves state-of-the-art performance while maintaining near-linear scalability with user sequence length. Our code is publicly available at https://github.com/ZhangYifeng1995/SSD4Rec.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑