Hao Qingbo, Wang Chundong, Xiao Yingyuan, Lin Hao
School of Computer Science and Engineering, Tianjin University of Technology, Binshui West Road, Tianjin, 300191 Tianjin China.
Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Ministry of Education, Binshui West Road, Tianjin, 300191 Tianjin China.
Appl Intell (Dordr). 2023;53(11):14668-14689. doi: 10.1007/s10489-022-04215-7. Epub 2022 Nov 1.
In the application recommendation field, collaborative filtering (CF) method is often considered to be one of the most effective methods. As the basis of CF-based recommendation methods, representation learning needs to learn two types of factors: attribute factors revealed by independent individuals (e.g., user attributes, application types) and interaction factors contained in collaborative signals (e.g., interactions influenced by others). However, existing CF-based methods fail to learn these two factors separately; therefore, it is difficult to understand the deeper motivation behind user behaviors, resulting in suboptimal performance. From this point of view, we propose a multi-granularity coupled graph neural network recommendation method based on implicit relationships (IMGC-GNN). Specifically, we introduce contextual information (time and space) into user-application interactions and construct a three-layer coupled graph. Then, the graph neural network approach is used to learn the attribute and interaction factors separately. For attribute representation learning, we decompose the coupled graph into three homogeneous graphs with users, applications, and contexts as nodes. Next, we use multilayer aggregation operations to learn features between users, between contexts, and between applications. For interaction representation learning, we construct a homogeneous graph with user-context-application interactions as nodes. Next, we use node similarity and structural similarity to learn the deep interaction features. Finally, according to the learned representations, IMGC-GNN makes accurate application recommendations to users in different contexts. To verify the validity of the proposed method, we conduct experiments on real-world interaction data from three cities and compare our model with seven baseline methods. The experimental results show that our method has the best performance in the top- recommendation.
在应用推荐领域，协同过滤（CF）方法通常被认为是最有效的方法之一。作为基于CF的推荐方法的基础，表征学习需要学习两类因素：由独立个体揭示的属性因素（例如，用户属性、应用类型）和协同信号中包含的交互因素（例如，受他人影响的交互）。然而，现有的基于CF的方法未能分别学习这两类因素；因此，很难理解用户行为背后更深层次的动机，导致性能欠佳。从这一角度出发，我们提出了一种基于隐式关系的多粒度耦合图神经网络推荐方法（IMGC-GNN）。具体而言，我们将上下文信息（时间和空间）引入用户与应用的交互中，并构建一个三层耦合图。然后，使用图神经网络方法分别学习属性和交互因素。对于属性表征学习，我们将耦合图分解为三个同构图，分别以用户、应用和上下文作为节点。接下来，我们使用多层聚合操作来学习用户之间、上下文之间以及应用之间的特征。对于交互表征学习，我们构建一个以用户-上下文-应用交互作为节点的同构图。接下来，我们使用节点相似度和结构相似度来学习深度交互特征。最后，根据学习到的表征，IMGC-GNN在不同上下文中为用户做出准确的应用推荐。为了验证所提方法的有效性，我们对来自三个城市的真实世界交互数据进行了实验，并将我们的模型与七种基线方法进行了比较。实验结果表明，我们的方法在top-推荐中具有最佳性能。
