Class-Imbalanced Learning on Graphs: A Survey
It tackles the challenge of imbalanced data in graph analysis for researchers and practitioners, but it is incremental as it surveys existing work rather than introducing new methods.
This survey addresses the problem of class imbalance in graph data, which hinders machine learning performance, by reviewing and categorizing existing methods in class-imbalanced learning on graphs (CILG) to provide a comprehensive overview and future research directions.
The rapid advancement in data-driven research has increased the demand for effective graph data analysis. However, real-world data often exhibits class imbalance, leading to poor performance of machine learning models. To overcome this challenge, class-imbalanced learning on graphs (CILG) has emerged as a promising solution that combines the strengths of graph representation learning and class-imbalanced learning. In recent years, significant progress has been made in CILG. Anticipating that such a trend will continue, this survey aims to offer a comprehensive understanding of the current state-of-the-art in CILG and provide insights for future research directions. Concerning the former, we introduce the first taxonomy of existing work and its connection to existing imbalanced learning literature. Concerning the latter, we critically analyze recent work in CILG and discuss urgent lines of inquiry within the topic. Moreover, we provide a continuously maintained reading list of papers and code at https://github.com/yihongma/CILG-Papers.