A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
It addresses the need for transparency in graph learning models, but is incremental as it synthesizes existing work rather than introducing new methods.
The paper surveys graph counterfactual explanations for Graph Neural Networks, analyzing 14 methods, 22 datasets, and 19 metrics to provide a taxonomy and empirical evaluation via the GRETEL library.
Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs. We analysed the SoA to provide a taxonomy, a uniform notation, and the benchmarking datasets and evaluation metrics. We discuss fourteen methods, their evaluation protocols, twenty-two datasets, and nineteen metrics. We integrated the majority of methods into the GRETEL library to conduct an empirical evaluation to understand their strengths and pitfalls. We highlight open challenges and future work.