Knowledge Graphs (KGs) have shown great success in recommendation. This is attributed to the rich attribute information contained in KG to improve item and user representations as side information. However, existing knowledge-aware methods leverage attribute information at a coarse-grained level both in item and user side. In this paper, we proposed a novel attentive knowledge graph attribute network(AKGAN) to learn item attributes and user interests via attribute information in KG. Technically, AKGAN adopts a heterogeneous graph neural network framework, which has a different design between the first layer and the latter layer. With one attribute placed in the corresponding range of element-wise positions, AKGAN employs a novel interest-aware attention network, which releases the limitation that the sum of attention weight is 1, to model the complexity and personality of user interests towards attributes. Experimental results on three benchmark datasets show the effectiveness and explainability of AKGAN.
翻译:知识图(KGs)显示在建议中取得了巨大成功,这归功于KG中包含的丰富属性信息,目的是改进项目和用户作为侧面信息的表述方式;然而,现有的知识意识方法在项目和用户方面都利用粗粗的分层信息;在本文中,我们提议建立一个新颖的注意知识图属性网络(AKGAN),以便通过KG的分层信息学习项目属性和用户兴趣;从技术上讲,AKGAN采用了一个复杂图形神经网络框架,在第一层和后层之间有不同的设计;AKGAN利用了一个新颖的注意兴趣网络,在相应的元素位置上设置了一个属性,它释放出注意的总量为1的局限性,以模拟用户对属性的兴趣的复杂性和个性;三个基准数据集的实验结果显示AKGAN的有效性和可解释性。