QGShap: Quantum Acceleration for Faithful GNN Explanations

TL;DR

QGShap introduces a quantum computing method that significantly accelerates the computation of exact Shapley value explanations for GNNs, ensuring high fidelity and interpretability in critical applications.

Contribution

It presents the first quantum approach leveraging amplitude amplification to compute exact Shapley values efficiently for GNN explanations.

Findings

Achieves quadratic speedup in coalition evaluation

Maintains exact Shapley computation without approximation

Demonstrates high fidelity and explanation accuracy on synthetic datasets

Abstract

Graph Neural Networks (GNNs) have become indispensable in critical domains such as drug discovery, social network analysis, and recommendation systems, yet their black-box nature hinders deployment in scenarios requiring transparency and accountability. While Shapley value-based methods offer mathematically principled explanations by quantifying each component's contribution to predictions, computing exact values requires evaluating $2^n$ coalitions (or aggregating over $n!$ permutations), which is intractable for real-world graphs. Existing approximation strategies sacrifice either fidelity or efficiency, limiting their practical utility. We introduce QGShap, a quantum computing approach that leverages amplitude amplification to achieve quadratic speedups in coalition evaluation while maintaining exact Shapley computation. Unlike classical sampling or surrogate methods, our approach provides fully faithful explanations without approximation trade-offs for tractable graph sizes. We conduct empirical evaluations on synthetic graph datasets, demonstrating that QGShap achieves consistently high fidelity and explanation accuracy, matching or exceeding the performance of classical methods across all evaluation metrics. These results collectively demonstrate that QGShap not only preserves exact Shapley faithfulness but also delivers interpretable, stable, and structurally consistent explanations that align with the underlying graph reasoning of GNNs. The implementation of QGShap is available at https://github.com/smlab-niser/qgshap.