Deep Learning on Knowledge Graph for Recommender System: A Survey

Abstract

Recent advances in research have demonstrated the effectiveness of knowledge graphs (KG) in providing valuable external knowledge to improve recommendation systems (RS). A knowledge graph is capable of encoding high-order relations that connect two objects with one or multiple related attributes. With the help of the emerging Graph Neural Networks (GNN), it is possible to extract both object characteristics and relations from KG, which is an essential factor for successful recommendations. In this paper, we provide a comprehensive survey of the GNN-based knowledge-aware deep recommender systems. Specifically, we discuss the state-of-the-art frameworks with a focus on their core component, i.e., the graph embedding module, and how they address practical recommendation issues such as scalability, cold-start and so on. We further summarize the commonly-used benchmark datasets, evaluation metrics as well as open-source codes. Finally, we conclude the survey and propose potential research directions in this rapidly growing field.

6 figures, 5 tables

References in corpus (6)

• Semi-Supervised Classification with Graph Convolutional Networks
• KGAT: Knowledge Graph Attention Network for Recommendation
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search
• IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation
• A Fairness-aware Hybrid Recommender System

Cited by in corpus (9)

• Recommender systems based on graph embedding techniques: A comprehensive review
• Multimodal Metadata Assignment for Cultural Heritage Artifacts
• Combining social relations and interaction data in Recommender System with Graph Convolution Collaborative Filtering
• Graph Learning based Recommender Systems: A Review
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• User Embedding based Neighborhood Aggregation Method for Inductive Recommendation
• Driver-Specific Risk Recognition in Interactive Driving Scenarios using Graph Representation
• Knowledge Graphs and Machine Learning in biased C4I applications
• Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation