A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks
This work addresses the need for generic and efficient counterfactual explainers in graph neural networks, which is important for interpretability in graph-based ML applications.
The paper introduces a pipeline for counterfactual explainability in GNNs that integrates factual explainers with link prediction models to generate high-quality explanations. Experiments on real and synthetic benchmarks show improvements over baselines across multiple metrics.
In this study, we propose a novel pipeline for generic, model-agnostic, local-level counterfactual explainability in graph neural networks (GNNs). Although counterfactual explainers capable of both adding and removing edges have emerged in recent years, the need for generic and efficient solutions remains unmet, particularly concerning qualitative explanation generation. Our approach couples progress in factual explainability with missing edge prediction models rooted in link prediction research, in order to enhance the quality, robustness and intuitiveness of explanations. A multi-faceted experimental analysis conducted on real-world and synthetic graph classification benchmarks, both binary and multi-label, demonstrates the advancements in comparison to state-of-the-art baselines across diverse metrics.