arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.16182cs.IR
收藏

TiM4Rec: 基于时间感知结构化状态空间对偶模型的高效序列推荐模型

TiM4Rec: An Efficient Sequential Recommendation Model Based on Time-Aware Structured State Space Duality Model

Hao Fan, Mengyi Zhu, Yanrong Hu, Hailin Feng, Zhijie He, Hongjiu Liu, Qingyang Liu

AI总结:

针对Mamba2的SSD架构在序列推荐低维场景下性能下降问题,提出TiM4Rec模型,通过引入时间感知结构化掩码矩阵将时间感知能力高效整合到SSD中,在保留计算效率的同时提升了推荐性能。

摘要:

序列推荐建模范式正从Transformer转向Mamba架构,该架构包含两代:基于状态空间模型(SSM)的Mamba1和基于状态空间对偶(SSD)的Mamba2。尽管SSD相比SSM具有更优的计算效率,但在序列推荐任务中存在性能下降问题,尤其是在对这些任务至关重要的低维场景下。考虑到时间感知增强方法通常用于缓解性能损失,我们的分析表明,SSD的性能下降同样可以通过利用时间感知方法中的机制从根本上得到补偿。因此,我们提出将时间感知集成到SSD框架中以解决这些性能问题。然而,将当前基于TiSASRec的时间感知方法集成到SSD面临以下挑战:1)将这些基于Transformer的机制与SSD架构集成的复杂性;2)时间差建模的维度扩展需求导致的计算低效。为克服这些挑战,我们引入一种新颖的时间感知结构化掩码矩阵,将时间感知能力高效整合到SSD中。基于此,我们提出用于推荐的时间感知Mamba(TiM4Rec),该模型在低维SSD场景下缓解了性能下降,同时保留了计算效率。这标志着专为序列推荐领域Mamba架构定制的时间感知增强方法的首次应用。在三个真实世界数据集上进行的大量实验证明了我们方法的优越性。我们模型的代码可在https://github.com/AlwaysFHao/TiM4Rec获取。

英文摘要:

The Sequential Recommendation modeling paradigm is shifting from Transformer to Mamba architecture, which comprises two generations: Mamba1, based on the State Space Model (SSM), and Mamba2, based on State Space Duality (SSD). Although SSD offers superior computational efficiency compared to SSM, it suffers performance degradation in sequential recommendation tasks, especially in low-dimensional scenarios that are critical for these tasks. Considering that time-aware enhancement methods are commonly employed to mitigate performance loss, our analysis reveals that the performance decline of SSD can similarly be fundamentally compensated by leveraging mechanisms in time-aware methods. Thus, we propose integrating time-awareness into the SSD framework to address these performance issues. However, integrating current time-aware methods, modeled after TiSASRec, into SSD faces the following challenges: 1) the complexity of integrating these transformer-based mechanisms with the SSD architecture, and 2) the computational inefficiency caused by the need for dimensionality expansion of time-difference modeling. To overcome these challenges, we introduce a novel Time-aware Structured Masked Matrix that efficiently incorporates time-aware capabilities into SSD. Building on this, we propose Time-Aware Mamba for Recommendation (TiM4Rec), which mitigates performance degradation in low-dimensional SSD contexts while preserving computational efficiency. This marks the inaugural application of a time-aware enhancement method specifically tailored for the Mamba architecture within the domain of sequential recommendation. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our approach. The code for our model is accessible at https://github.com/AlwaysFHao/TiM4Rec.

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。

↑