Graph neural networks for network science: A mini review

Graph Neural Networks (GNNs), a class of neural networks specifically designed to handle graph-structured data, have emerged as a hot research topic in fields such as data mining, machine learning, and biomedical engineering. Network science studies the properties and behaviors of complex networks, with graphs serving as the mathematical abstraction of these systems. In recent years, GNN technology has demonstrated significant application potential in network science. In this letter, we provide a mini review of different types of GNNs, as well as their applications in important network science tasks, particularly in nodes and edges identification as well as network robustness. Finally, we discuss the promising future research directions.