A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
It provides a comprehensive overview for researchers working on graph learning with heterophily, but it is incremental as it synthesizes existing literature rather than introducing new methods.
This survey reviews over 500 publications on learning from heterophilic graphs, where linked nodes tend to have different labels, covering metrics, datasets, methods, and applications to address this problem in graph-structured data.
Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar features, have recently attracted significant attention and found many real-world applications. Meanwhile, increasing efforts have been made to advance learning from graphs with heterophily. Various graph heterophily measures, benchmark datasets, and learning paradigms are emerging rapidly. In this survey, we comprehensively review existing works on learning from graphs with heterophily. First, we overview over 500 publications, of which more than 340 are directly related to heterophilic graphs. After that, we survey existing metrics of graph heterophily and list recent benchmark datasets. Further, we systematically categorize existing methods based on a hierarchical taxonomy including GNN models, learning paradigms and practical applications. In addition, broader topics related to graph heterophily are also included. Finally, we discuss the primary challenges of existing studies and highlight promising avenues for future research.