MaTrRec：结合Mamba与Transformer用于序列推荐
MaTrRec: Uniting Mamba and Transformer for Sequential Recommendation
AI总结：
针对Mamba在短序列推荐中效果受限及冷启动问题，提出结合Mamba与Transformer优势的MaTrRec模型，在长短序列上均提升预测能力并改善冷启动，在五个数据集上达到SOTA。
摘要：
序列推荐系统旨在通过分析用户行为序列中的动态偏好和依赖关系来提供个性化推荐。近期，Transformer模型能够有效捕捉用户偏好。然而，其二次方的计算复杂度限制了在长交互序列数据上的推荐性能。受状态空间模型（SSM）代表模型Mamba的启发，该模型能以线性复杂度高效捕捉长交互序列中的用户偏好，我们发现Mamba在短交互序列中的推荐效果有限，无法召回用户实际感兴趣的物品，并加剧了数据稀疏性冷启动问题。为解决此问题，我们创新性地提出新模型MaTrRec，结合了Mamba和Transformer的优势。该模型充分利用Mamba在处理长程依赖上的优势以及Transformer在短程依赖上的全局注意力优势，从而在长、短交互序列数据集上均增强了预测能力，同时平衡了模型效率。值得注意的是，我们的模型显著改善了数据稀疏性冷启动问题，在高度稀疏的Amazon Musical Instruments数据集上提升了高达33%。我们在五个广泛使用的公开数据集上进行了广泛的实验评估。实验结果表明，我们的模型在所有五个数据集上均优于当前最先进的序列推荐模型。代码可在https://github.com/Unintelligentmumu/MaTrRec获取。
英文摘要：
Sequential recommendation systems aim to provide personalized recommendations by analyzing dynamic preferences and dependencies within user behavior sequences. Recently, Transformer models can effectively capture user preferences. However, their quadratic computational complexity limits recommendation performance on long interaction sequence data. Inspired by the State Space Model (SSM)representative model, Mamba, which efficiently captures user preferences in long interaction sequences with linear complexity, we find that Mamba's recommendation effectiveness is limited in short interaction sequences, with failing to recall items of actual interest to users and exacerbating the data sparsity cold start problem. To address this issue, we innovatively propose a new model, MaTrRec, which combines the strengths of Mamba and Transformer. This model fully leverages Mamba's advantages in handling long-term dependencies and Transformer's global attention advantages in short-term dependencies, thereby enhances predictive capabilities on both long and short interaction sequence datasets while balancing model efficiency. Notably, our model significantly improves the data sparsity cold start problem, with an improvement of up to 33% on the highly sparse Amazon Musical Instruments dataset. We conducted extensive experimental evaluations on five widely used public datasets. The experimental results show that our model outperforms the current state-of-the-art sequential recommendation models on all five datasets. The code is available at https://github.com/Unintelligentmumu/MaTrRec.
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。
