In recent years, people have become more interested in expanding deep learning methods on graphs, and a lot of progress has been made in the field. Although traditional deep learning methods have been applied to extract the features of Euclidean spatial data with great success, the data in many practical application scenarios are generated from non-Euclidean spaces. The performance of traditional deep learning methods in processing non-Euclidean spatial data is still not optimistic. Driven by the success of many factors, the researchers used the ideas of convolutional networks, recurrent networks, and deep autoencoders to define and design the neural network structure for processing graph data. This is a new research hotspot— Graph Neural Networks (GNNs). It is necessary to summarize the latest GNNs-related studies and propose improved algorithms to further promote breakthroughs in more applications of GNNs. This paper mainly provides an overview of the current research status of graph neural networks and proposes future work from three aspects.