Measuring What Matters: A Unified Evaluation Framework for GNN Explainability
This work addresses the lack of consistent evaluation practices in GNN explainability, providing a standardized framework for practitioners to select trustworthy explainers.
The paper introduces a unified, quantitative benchmarking framework for GNN explainability that requires no ground-truth assumptions, formalizing tabular explainability metrics for graph data. Through large-scale benchmarking, it identifies Pareto-optimal explainers and provides actionable usability guidelines for practitioners.
Graph eXplainable AI (G-XAI) is increasingly important for making Graph Neural Networks interpretable and accountable. While a growing number of explainers are available, choosing the right method and assessing the trustworthiness of its outputs remains unclear. Consistent evaluation practices and actionable guidance are still missing, hindering practical adoption. In this paper, we introduce a unified, quantitative benchmarking framework for G-XAI that requires no ground-truth assumptions. We formalize tabular explainability metrics for graph data, evaluating topological structure and node features as independent components. Our large-scale benchmarking study identifies explainers that consistently lie on the Pareto front across metric pairs and tasks, establishing robustly non-dominated solutions - while confirming that no single explainer achieves universal superiority. We distill our findings into actionable G-XAI usability guidelines to support Machine Learning practitioners in evaluating and deploying trustworthy GNN-based pipelines.