赋能序列推荐：协同信号与语义相关性的融合
Empowering Sequential Recommendation from Collaborative Signals and Semantic Relatedness
AI总结：
本文提出TSSR，一种双流架构，融合协同信号与语义相关性，通过分层对比模块对齐跨模态表示，提升序列推荐性能，并在五个数据集上验证了其优越性。
摘要：
序列推荐系统（SRS）通过建模按时间排序的历史行为来捕捉动态的用户偏好。尽管有效，但仅关注行为中的协同信号并不能完全把握用户兴趣。建模内容特征（如图像和文本）中反映的语义相关性同样重要。为此，在本文中，我们旨在通过有效统一协同信号和语义相关性来增强SRS任务。值得注意的是，我们通过实验指出，由于语义鸿沟问题，实现这一目标并非易事。因此，我们提出了一种端到端的双流架构用于序列推荐，命名为TSSR，以从基于ID的序列和基于内容的序列中学习用户偏好。具体来说，我们首先提出了新颖的分层对比模块，包括粗粒度的用户级和细粒度的物品级术语，以对齐跨模态的表示。此外，我们还设计了一种双流架构来学习模态内序列的依赖性和模态间序列的复杂交互，这可以在理解用户兴趣方面产生更强的表达能力。我们在五个公开数据集上进行了大量实验。实验结果表明，TSSR能够产生优于竞争基线的性能。我们还公开了实验代码，网址为https://github.com/Mingyue-Cheng/TSSR。
英文摘要：
Sequential recommender systems (SRS) could capture dynamic user preferences by modeling historical behaviors ordered in time. Despite effectiveness, focusing only on the \textit{collaborative signals} from behaviors does not fully grasp user interests. It is also significant to model the \textit{semantic relatedness} reflected in content features, e.g., images and text. Towards that end, in this paper, we aim to enhance the SRS tasks by effectively unifying collaborative signals and semantic relatedness together. Notably, we empirically point out that it is nontrivial to achieve such a goal due to semantic gap issues. Thus, we propose an end-to-end two-stream architecture for sequential recommendation, named TSSR, to learn user preferences from ID-based and content-based sequence. Specifically, we first present novel hierarchical contrasting module, including coarse user-grained and fine item-grained terms, to align the representations of inter-modality. Furthermore, we also design a two-stream architecture to learn the dependence of intra-modality sequence and the complex interactions of inter-modality sequence, which can yield more expressive capacity in understanding user interests. We conduct extensive experiments on five public datasets. The experimental results show that the TSSR could yield superior performance than competitive baselines. We also make our experimental codes publicly available at https://github.com/Mingyue-Cheng/TSSR.
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。
