A Comprehensive Survey of Graph Neural Networks for Knowledge Graphs

• Published in: IEEE access Vol. 10; pp. 75729 - 75741
• Main Authors: Ye, Zi, Kumar, Yogan Jaya, Sing, Goh Ong, Song, Fengyan, Wang, Junsong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial intelligence; Cognition; Deep learning; distributed embedding; graph neural network; Graph neural networks; Graphical representations; Graphs; Internet; Knowledge engineering; knowledge graph; Knowledge management; Knowledge representation; Machine learning; Neural networks; Predictive models; Recommender systems; representation learning; Structured data; Task analysis
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2022.3191784

The Knowledge graph, a multi-relational graph that represents rich factual information among entities of diverse classifications, has gradually become one of the critical tools for knowledge management. However, the existing knowledge graph still has some problems which form hot research topics in recent years. Numerous methods have been proposed based on various representation techniques. Graph Neural Network, a framework that uses deep learning to process graph-structured data directly, has significantly advanced the state-of-the-art in the past few years. This study firstly is aimed at providing a broad, complete as well as comprehensive overview of GNN-based technologies for solving four different KG tasks, including link prediction, knowledge graph alignment, knowledge graph reasoning, and node classification. Further, we also investigated the related artificial intelligence applications of knowledge graphs based on advanced GNN methods, such as recommender systems, question answering, and drug-drug interaction. This review will provide new insights for further study of KG and GNN.