A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges

Abstract

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.

References in corpus (4)

• GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks
• Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
• Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation
• GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation

Cited by in corpus (4)

• A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification
• Counterfactual Explanations for Deep Learning-Based Traffic Forecasting
• Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference
• GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks