[论文解读] Position-enhanced and Time-aware Graph Convolutional Network for Sequential Recommendations

Liwei Huang, Yutao Ma+5 more|arXiv (Cornell University)|Jul 12, 2021

Recommender Systems and Techniques被引用 5

一句话总结

该论文提出PTGCN，一种增强位置感知与时间敏感的图卷积网络，用于序列推荐。该方法通过二部图建模用户-物品交互，利用新型图卷积操作捕捉序列顺序与时间动态。在三个真实世界数据集上，PTGCN优于最先进模型，通过高阶连通性与动态用户-物品表征学习，显著提升排序性能。

ABSTRACT

Most of the existing deep learning-based sequential recommendation approaches utilize the recurrent neural network architecture or self-attention to model the sequential patterns and temporal influence among a user's historical behavior and learn the user's preference at a specific time. However, these methods have two main drawbacks. First, they focus on modeling users' dynamic states from a user-centric perspective and always neglect the dynamics of items over time. Second, most of them deal with only the first-order user-item interactions and do not consider the high-order connectivity between users and items, which has recently been proved helpful for the sequential recommendation. To address the above problems, in this article, we attempt to model user-item interactions by a bipartite graph structure and propose a new recommendation approach based on a Position-enhanced and Time-aware Graph Convolutional Network (PTGCN) for the sequential recommendation. PTGCN models the sequential patterns and temporal dynamics between user-item interactions by defining a position-enhanced and time-aware graph convolution operation and learning the dynamic representations of users and items simultaneously on the bipartite graph with a self-attention aggregator. Also, it realizes the high-order connectivity between users and items by stacking multi-layer graph convolutions. To demonstrate the effectiveness of PTGCN, we carried out a comprehensive evaluation of PTGCN on three real-world datasets of different sizes compared with a few competitive baselines. Experimental results indicate that PTGCN outperforms several state-of-the-art models in terms of two commonly-used evaluation metrics for ranking.

研究动机与目标

• 解决现有序列推荐模型忽略物品动态与高阶用户-物品连通性的局限性。
• 通过将位置与时间感知整合进图卷积网络，建模用户与物品随时间的动态变化。
• 在二部用户-物品交互图上，同时学习用户与物品的动态、时间敏感表征。
• 通过多层图卷积捕捉高阶连通性，提升序列推荐性能。

提出的方法

• 构建二部用户-物品交互图以表示序列行为。
• 设计一种增强位置感知与时间敏感的图卷积操作，编码交互间的序列顺序与时间差异。
• 采用自注意力聚合器，在图中消息传递过程中动态加权邻居节点。
• 堆叠多层图卷积以捕捉用户与物品间的高阶连通性。
• 学习随时间与序列位置动态演化的用户与物品嵌入表征。
• 整合位置编码与时间敏感注意力，同步建模时间影响与序列模式。

实验结果

研究问题

• RQ1 基于图的方法能否有效建模用户-物品交互中的序列模式与时间动态？
• RQ2 将位置与时间信息整合进图卷积对序列推荐性能有何影响？
• RQ3 建模用户与物品间的高阶连通性在多大程度上提升推荐准确率？
• RQ4 在不同数据集上，PTGCN与最先进模型在排序指标上的表现如何比较？

主要发现

• PTGCN在三个真实世界数据集上达到最先进性能，精度与召回率均优于现有模型。
• 位置与时间感知的集成显著提升模型捕捉序列动态与时间偏好能力。
• 多层图卷积的使用有效建模了高阶用户-物品连通性，从而增强推荐准确率。
• 自注意力聚合器有效捕捉了序列中用户与物品间的动态依赖关系。
• 消融实验确认，位置编码与时间感知机制均对性能提升有显著贡献。
• 模型在不同规模的数据集上均表现出良好泛化能力，表明其具备鲁棒性与可扩展性。