Feature Importance and Explainability in Quantum Machine Learning

TL;DR

This paper compares feature importance and explainability techniques between classical and quantum machine learning models using the Iris dataset, highlighting the potential and challenges of QML interpretability.

Contribution

It introduces a comparative analysis of explainability methods applied to quantum and classical ML models, demonstrating how quantum models can be interpreted.

Findings

Quantum models show comparable feature importance insights to classical models.

Explainability methods like SHAP and ALE can be adapted for QML models.

Quantum models exhibit unique interpretability challenges and opportunities.

Abstract

Many Machine Learning (ML) models are referred to as black box models, providing no real insights into why a prediction is made. Feature importance and explainability are important for increasing transparency and trust in ML models, particularly in settings such as healthcare and finance. With quantum computing's unique capabilities, such as leveraging quantum mechanical phenomena like superposition, which can be combined with ML techniques to create the field of Quantum Machine Learning (QML), and such techniques may be applied to QML models. This article explores feature importance and explainability insights in QML compared to Classical ML models. Utilizing the widely recognized Iris dataset, classical ML algorithms such as SVM and Random Forests, are compared against hybrid quantum counterparts, implemented via IBM's Qiskit platform: the Variational Quantum Classifier (VQC) and Quantum Support Vector Classifier (QSVC). This article aims to provide a comparison of the insights generated in ML by employing permutation and leave one out feature importance methods, alongside ALE (Accumulated Local Effects) and SHAP (SHapley Additive exPlanations) explainers.