Graph Neural Networks: A bibliometrics overview

• Published in: Machine learning with applications Vol. 10; p. 100401
• Main Authors: Keramatfar, Abdalsamad, Rafiee, Mohadeseh, Amirkhani, Hossein
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.12.2022; Elsevier
• Subjects: Bibliometrics; Graph Convolutional Network; Graph Neural Network; Graph representation learning; Graph representation learning; Graph Convolutional Network; Bibliometrics; Graph Neural Network
• ISSN: 2666-8270; 2666-8270
• DOI: 10.1016/j.mlwa.2022.100401

Recently, graph neural networks (GNN) have become a hot topic in machine learning community. This paper presents a Scopus-based bibliometric overview of the GNNs’ research since 2004 when GNN papers were first published. The study aims to evaluate GNN research trends, both quantitatively and qualitatively. We provide the trend of research, distribution of subjects, active and influential authors and institutions, sources of publications, most cited documents, and hot topics. Our investigations reveal that the most frequent subject categories in this field are computer science, engineering, and telecommunications. In addition, the most active source of GNN publications is Lecture Notes in Computer Science. The most prolific or impactful institutions are found in the United States, China, and Canada. We also provide must-read papers based on citation count and future directions. Our analysis reveals that node classification is the most popular task, followed by link prediction, and graph classification in the GNN literature. Moreover, the results suggest that the application of graph convolutional networks and attention mechanisms are now among hot topics of GNN research. Finally, scalability, generalization, over-smoothing, and explainability of graph neural networks are some research directions to pursue. •Graph Convolutional Networks and attention mechanism are now hot topics in GNN research.•Node classification is the most popular task, followed by link prediction, and graph classification in the GNN literature.•Scalability, generalization, over-smoothing, and explainability of graph neural networks are some research directions to pursue.