Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Maria Myrto Villia, Filippos Gouidis, Theodore Patkos, Panos Trahanias• 2026

Related benchmarks

TaskDatasetResultRank
Graph Counterfactual ExplanationsBA-2MOTIFS
Avg Minimality Score100
16
Motif Proximity EvaluationBA-2MOTIFS
Motif Proximity Score90
10
Motif Proximity EvaluationBA 2Motifs 3Classes
Motif Proximity Score90
10
Motif Proximity EvaluationBA-3Motifs
Motif Proximity Score0.98
10
Graph Counterfactual ExplanationTwitter
Minimality Score100
10
Graph Counterfactual ExplanationsBA-3Motifs
Avg Minimality Score1
10
Graph Counterfactual ExplanationsBA-4Motifs
Average Minimality Score1
10
Graph Counterfactual ExplanationsGRAPH-SST5
Average Minimality Score99
10
Motif Proximity EvaluationBA-4Motifs
Motif Proximity Score0.94
10
Graph Counterfactual ExplanationBA-3Motifs
Validity94
10
Showing 10 of 28 rows

Other info

Follow for update