GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks
Kenza Amara,
Rex Ying,
Ce Zhang.
GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks. .
Jun, 2022.
Abstract
In this paper, we propose the first systematic evaluation framework for GNN explainability, considering explainability on three different “user needs:” explanation focus, mask nature, and mask transformation. We propose a unique metric that combines the fidelity measures and classify explanations based on their quality of being sufficient or necessary.