A Novel Approach to Explainable AI with Quantized Active Ingredients in Decision Making

2025-11-19

2025 9th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)

AI Summary

This work proposes an interpretable AI framework integrating quantum computing principles to address the challenge of identifying critical decision features in high-risk AI systems, where opacity often impedes trust and accountability. For the first time, a quantum-classical hybrid architecture is introduced for feature attribution analysis, leveraging quantum Boltzmann machines (QBMs) alongside classical Boltzmann machines (CBMs), both trained on a reduced-dimension binary MNIST dataset. The study innovatively introduces the concept of “quantized active components” to explicitly highlight salient features. Evaluation via gradient-based saliency maps and SHAP reveals that QBMs significantly outperform CBMs, achieving higher classification accuracy (83.5% vs. 54%) and greater attribution concentration, as evidenced by lower entropy (1.27 vs. 1.39), thereby demonstrating a superior balance between predictive performance and interpretability.

Technology Category

• Machine Learning: Quantum Machine Learning
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• Explainable AI
• Interpretability
• Quantum Computing
• Decision Making
• Feature Attribution

Innovation

• Explainable AI
• Quantum Boltzmann Machine
• Hybrid Quantum-Classical Model
• Feature Attribution
• Saliency Maps