摘要：Recommender systems (RS) have been developed to make personalized suggestions andenrich users’ preferences in various online applications to address the information explosion problems.However, traditional recommender-based systems act as black boxes, not presenting the user withinsights into the system logic or reasons for recommendations. Recently, generating explainablerecommendations with deep knowledge graphs (DKG) has attracted significant attention. DKG isa subset of explainable artificial intelligence (XAI) that utilizes the strengths of deep learning (DL)algorithms to learn, provide high-quality predictions, and complement the weaknesses of knowledgegraphs (KGs) in the explainability of recommendations. DKG-based models can provide moremeaningful, insightful, and trustworthy justifications for recommended items and alleviate theinformation explosion problems. Although several studies have been carried out on RS, only a fewpapers have been published on DKG-based methodologies, and a review in this new research directionis still insufficiently explored. To fill this literature gap, this paper uses a systematic literature reviewframework to survey the recently published papers from 2018 to 2022 in the landscape of DKG andXAI. We analyze how the methods produced in these papers extract essential information from graph-based representations to improve recommendations’ accuracy, explainability, and reliability. From theperspective of the leveraged knowledge-graph related information and how the knowledge-graphor path embeddings are learned and integrated with the DL methods, we carefully select and classifythese published works into four main categories: the Two-stage explainable learning methods, theJoint-stage explainable learning methods, the Path-embedding explainable learning methods, andthe Propagation explainable learning methods. We further summarize these works according to thecharacteristics of the approaches and the recommendation scenarios to facilitate the ease of checkingthe literature. We finally conclude by discussing some open challenges left for future research in thisvibrant field.
关键词：deep neural network embeddings;explainable artificial intelligence;knowledge graphembeddings;relational learning;recommender systems
