Imbalanced node classification on graphs with graph neural networks: A survey

Imbalanced node classification is an important research topic in graph learning. With the rise of deep learning, powerful models like graph neural networks (GNNs) have been widely used in node classification tasks and achieved promising performance. However, real-world graphs are usually imbalanced, characterized by some classes having an adequate amount of data while others lack data. This imbalance presents the suboptimal classification performance of the model. Therefore, research on the GNNs-based imbalanced node classification is crucial. This article aims to systematically summarize the development status of GNNs in imbalanced node classification. First, the related concepts of GNNs and imbalanced node classification are introduced to establish a solid foundation for readers. Second, the methods are divided into data-level methods and algorithm-level methods, then subdivided into seven subcategories. Especially, we discuss the key thoughts, relative strengths, and weaknesses of classic methods in each subcategory. Then, datasets and common evaluation metrics are compiled to provide a wealth of useful resources. Finally, future research directions for imbalanced node classification on graphs are introduced to promote the boom of this field.