Q-SHAP: Explainable AI for Quantum Circuits via Quantum-Native and Hybrid Classical Approaches

M. Ramu, Donapati Deepika, Nikhila Baddula +3 more

A. M. A. S. D. Alagiyawanna, Asoka Karunananda, Thushari Silva +1 more

Artificial Intelligence (AI) systems have shown good success at classifying. However, the lack of explainability is a true and significant challenge, especially in high-stakes domains, such as health and finance, where understanding is paramount. We propose a new solution to this challenge: an explainable AI framework based on our comparative study with Quantum Boltzmann Machines (QBMs) and Classical Boltzmann Machines (CBMs). We leverage principles of quantum computing within classical machine learning to provide substantive transparency around decision-making. The design involves training both models on a binarised and dimensionally reduced MNIST dataset, where Principal Component Analysis (PCA) is applied for preprocessing. For interpretability, we employ gradient-based saliency maps in QBMs and SHAP (SHapley Additive exPlanations) in CBMs to evaluate feature attributions.QBMs deploy hybrid quantum-classical circuits with strongly entangling layers, allowing for richer latent representations, whereas CBMs serve as a classical baseline that utilises contrastive divergence. Along the way, we found that QBMs outperformed CBMs on classification accuracy (83.5% vs. 54%) and had more concentrated distributions in feature attributions as quantified by entropy (1.27 vs. 1.39). In other words, QBMs not only produced better predictive performance than CBMs, but they also provided clearer identification of "active ingredient" or the most important features behind model predictions. To conclude, our results illustrate that quantum-classical hybrid models can display improvements in both accuracy and interpretability, which leads us toward more trustworthy and explainable AI systems.

Patrick Steinmüller, Schulz, Tobias, Ferdinand Graf +1 more

Parametrized Quantum Circuits (PQCs) enable a novel method for machine learning (ML). However, from a computational point of view they present a challenge to existing eXplainable AI (xAI) methods. On the one hand, measurements on quantum circuits introduce probabilistic errors which impact the convergence of these methods. On the other hand, the phase space of a quantum circuit expands exponentially with the number of qubits, complicating efforts to execute xAI methods in polynomial time. In this paper we will discuss the performance of established xAI methods, such as Baseline SHAP and Integrated Gradients. Using the internal mechanics of PQCs we study ways to speed up their computation.

Shyam R. Sihare, Aswani Kumar Cherukuri

Omar Albalooshi, Alavikunhu Panthakkan, Hussam Al Hamadi

Fake reviews pose a critical challenge to consumer trust and platform integrity in digital marketplaces. This paper introduces a hybrid quantum-classical machine learning framework for detecting fake reviews, leveraging quantum enhancements to improve predictive accuracy. Using the Amazon Fake Reviews dataset, baseline performance is established with classical classifiers, including Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes (NB), Random Forest (RF), and Logistic Regression (LR). Quantum machine learning (QML) models employing Amplitude Embedding and entanglement-driven circuits are integrated with classical models to form hybrid classifiers. A meta-classifier combining quantum and classical embeddings further boosts model performance, achieving up to 98.10 % accuracy. To ensure interpretability, eXplainable AI (XAI) techniques, such as SHAP and LIME, are applied to analyze predictions and identify key linguistic features. This work demonstrates the potential of quantum-augmented AI for trust-critical applications in e-commerce, paving the way for future advancements in quantum-enhanced machine learning.

Bhavya M. Patel