Despite that existing knowledge graphs embedding (KGE) based methods can achieve better recommendation performance compared with deep learning based ones, such improvement is limited due to lack of capturing the shared information between user-item interaction and item-item relation encoded in knowledge graph (KG) by fully leveraging the implicit and explicit relationship. To address this issue, in this paper, we propose a principled deep knowledge-enhanced network (DKEN) framework based on deep learning and KGE to model the semantics of entities and relations encoded in the KG. In particular, the DKEN utilizes deep neural networks (DNN) to learn higher-order feature interactions and ensembles KGE features with DNN features into an end-to-end learning process naturally to exploit implicit interaction and explicitt semantic features. Furthermore, a cross information sharing (CIS) layer is designed to facilitate information sharing between items and entities, and two aggregators are developed to improve the performance of the model. Extensive experiments on several public datasets, as well as online AB tests of an industrial recommendation scenario in the Ant Financial Service Group, demonstrate that DKEN achieves remarkably better performance than several state-of-the-art baselines.

尽管现有的基于知识图嵌入（KGE）的方法与基于深度学习的方法相比可以实现更好的推荐性能，但是由于缺少捕获知识图中编码的用户-项目交互和项目-项目关系之间的共享信息，因此这种改进受到限制（ KG）通过充分利用隐式和显式关系。为了解决这个问题，在本文中，我们提出了一个基于深度学习和KGE的有原则的深度知识增强网络（DKEN）框架，以对KG中编码的实体和关系的语义进行建模。特别是，DKEN利用深度神经网络（DNN）学习高阶特征交互并将KGE特征与DNN特征整合到端到端学习过程中，从而自然地利用隐式交互和显式语义特征。此外，跨信息共享（CIS）层旨在促进项目和实体之间的信息共享，并且开发了两个聚合器来提高模型的性能。在多个公共数据集上进行的大量实验以及蚂蚁金服服务集团对工业推荐方案的在线AB测试表明，DKEN的性能明显优于几个最新的基准。