The Application of Graph Neural Network in Natural Language Processing and Computer Vision

Abstract

Graphs can represent information transformation via geometrical relations, which have been well studied and applied in various research areas. A graph-based learning network named Graph Neural Network (GNN) arose with the vast development of deep learning in recent years. Unlike traditional deep learning networks such as CNN and RNN, GNN is superior in dealing with non-Euclidean graph data. This survey focuses on two widespread application fields of GNN, natural language processing (NLP) and computer vision (CV). Firstly, based on the tasks they perform, we categorize the most popular research sub-domains of NLP and CV, purpose a detailed review on the application of GNN in these areas. Secondly, we thoroughly analyzed the benchmark datasets applied in the GNN models while comparing them with different evaluation metrics. Finally, we briefly discuss the potential future direction of GNN according to its model building procedure and related application branches.