| 摘要: |
| 标签感知推荐算法利用标签标注数据提升推荐模型对用户偏好和项目属性的理解, 受到业界的广泛关注. 但是, 现有方法常忽视了用户关注点、项目属性和标签含义的多样性, 干扰了三者关系推断, 从而影响推荐结果. 因此, 提出一种基于解耦图神经网络的可解释标签感知推荐算法(DETRec), 解构用户、项目和标签的关注角度, 并由此形成可解释的推荐依据. 具体来讲, DETRec构造关系图以建模用户、项目和标签的关系; 通过邻域路由机制和消息传播机制, 分离结点形成属性子图, 以描述不同属性下的结点关系; 最终根据属性子图形成推荐依据. 实现了两种DETRec实例: 单图实例(DETRec-S)在单个关系图中描述全部结点关系; 多图实例(DETRec-M)使用3个二分图分别描述用户-项目、项目-标签、用户-标签关系. 在3个公开数据集上进行的大量实验表明, DETRec的两种实例均明显优于标签感知推荐的基准模型, 也为推荐结果生成了对应的推荐依据, 是有效的可解释标签感知推荐算法. |
| 关键词: 多媒体推荐 标签感知推荐 可解释推荐 特征解耦 图神经网络 |
| DOI：10.13328/j.cnki.jos.006754 |
| 分类号:TP18 |
| 基金项目:国家自然科学基金(62172226); 江苏省“双创博士”人才计划 (JSSCBS20210200) |
|
| Explainable Tag-aware Recommendation Based on Disentangled Graph Neural Network |
|
DU Xiao-Yu, CHEN Zheng, XIANG Xin-Guang
|
|
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
|
| Abstract: |
| Tag-aware recommendation algorithms use tagged data to enhance the recommendation models’ understanding of user preferences and item attributes, which attract extensive attention in the field. Most existing methods, however, neglect the diversities of user concerns, item attributes, and tag semantics and interfere with the correlation inference of the three, which affects the recommendation results. Therefore, this study introduces the disentangled graph neural network (DGNN) method into the tag-aware recommendation task and proposes a DGNN-based explainable tag-aware recommendation (DETRec) method. It disentangles the perspectives of users, items, and tags to provide explainable recommendation references. Specifically, DETRec utilizes a correlation graph construction module to model the user-item-tag correlations. Then, it employs a neighborhood routing mechanism and a message propagation mechanism to disentangle the nodes to form the sub-graphs of attributes and thereby describe the nodal correlations under different attributes. Finally, it generates recommendation references on the basis of these attribute sub-graphs. This study implements two types of DETRec instantiation: 1) DETRec based on a single graph (DETRec-S), which describes all correlations of user, item, and tag nodes in a single graph, and 2) DETRec based on multiple graphs (DETRec-M), which utilizes three bipartite graphs to describe the user-item, item-tag, and user-tag correlations separately. Extensive experiments on three public datasets demonstrate that the above two types of DETRec instantiation are significantly superior to the baseline model and generate the references corresponding to the recommendation results. Hence, DETRec is an effective explainable tag-aware recommendation algorithm. |
| Key words: multimedia recommendation tag-aware recommendation explainable recommendation embedding disentanglement graph neural network (GNN) |
