cs.LGJun 20, 2026

A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks

Authors: Maria Myrto VilliaFilippos GouidisTheodore PatkosPanos Trahanias

Organizations: Institute of Computer Science, Foundation for Research and Technology - Hellas (FORTH), Heraklion, Greece · Computer Science Department, University of Crete, Greece

Abstract

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.

Explore similar work

CardsList