COMBINEX: A Unified Counterfactual Explainer for Graph Neural Networks via Node Feature and Structural Perturbations

TL;DR

COMBINEX introduces a unified method for generating counterfactual explanations in GNNs by jointly perturbing node features and graph structure, improving interpretability and applicability across diverse datasets.

Contribution

It is the first approach to simultaneously optimize both node feature and structural perturbations for counterfactual explanations in GNNs.

Findings

Outperforms existing methods in explanation quality.

Effectively handles both continuous and discrete features.

Demonstrates robustness across multiple datasets and architectures.

Abstract

Counterfactual explanations have emerged as a powerful tool to unveil the opaque decision-making processes of graph neural networks (GNNs). However, existing techniques primarily focus on edge modifications, often overlooking the crucial role of node feature perturbations in shaping model predictions. To address this limitation, we propose COMBINEX, a novel GNN explainer that generates counterfactual explanations for both node and graph classification tasks. Unlike prior methods, which treat structural and feature-based changes independently, COMBINEX optimally balances modifications to edges and node features by jointly optimizing these perturbations. This unified approach ensures minimal yet effective changes required to flip a model's prediction, resulting in realistic and interpretable counterfactuals. Additionally, COMBINEX seamlessly handles both continuous and discrete node features, enhancing its versatility across diverse datasets and GNN architectures. Extensive experiments on real-world datasets and various GNN architectures demonstrate the effectiveness and robustness of our approach over existing baselines.