Feature Importance and Explainability in Quantum Machine Learning

TL;DR

The paper investigates how feature importance and explainability techniques can be applied to quantum machine learning (QML) models and compares them with classical ML using the Iris dataset. It implements classical SVM and Random Forest alongside quantum hybrids VQC and QSVC via IBM Qiskit, evaluating them with Leave-One-Out, Permutation, SHAP, and ALE explainers. Findings indicate QSVC often matches or surpasses classical performance on Iris, with feature-importance signals varying between quantum and classical models; petal features commonly dominate classical models while VQC shows distinctive sensitivities. The work demonstrates the feasibility of explainable quantum ML (XQAI) and highlights future needs for larger real quantum hardware studies and quantum-specific explainability methods.

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.

Figures (32)

• Figure 1: Classical Data on Quantum Algorithms. We are using Classical data with Quantum algorithms. Image adapted from schrodingerscatcartoon.
• Figure 2: Data Flow of the article, centring around the application of Feature Importance and Explainability.
• Figure 3: Non-Linear Support Vector Machine. Image adapted from nonlinearsvm.
• Figure 4: Quantum Advantage. Image adapted from quantum_advantage_ibm.
• Figure 5: 3D representation of a qubits’ possible states.