QuXAI: Explainers for Hybrid Quantum Machine Learning Models

TL;DR

This paper introduces QuXAI, a novel explainability framework for hybrid quantum-classical machine learning models, enhancing interpretability by visualizing feature attributions and separating quantum noise from influential classical features.

Contribution

It presents Q-MEDLEY, an explainer tailored for HQML models that combines feature inference with quantum transformation visualization, addressing a key gap in quantum AI explainability.

Findings

Q-MEDLEY effectively identifies influential classical features in HQML models.

It separates quantum noise from meaningful features, improving interpretability.

The approach outperforms existing classical XAI techniques in validation tests.

Abstract

The emergence of hybrid quantum-classical machine learning (HQML) models opens new horizons of computational intelligence but their fundamental complexity frequently leads to black box behavior that undermines transparency and reliability in their application. Although XAI for quantum systems still in its infancy, a major research gap is evident in robust global and local explainability approaches that are designed for HQML architectures that employ quantized feature encoding followed by classical learning. The gap is the focus of this work, which introduces QuXAI, an framework based upon Q-MEDLEY, an explainer for explaining feature importance in these hybrid systems. Our model entails the creation of HQML models incorporating quantum feature maps, the use of Q-MEDLEY, which combines feature based inferences, preserving the quantum transformation stage and visualizing the resulting attributions. Our result shows that Q-MEDLEY delineates influential classical aspects in HQML models, as well as separates their noise, and competes well against established XAI techniques in classical validation settings. Ablation studies more significantly expose the virtues of the composite structure used in Q-MEDLEY. The implications of this work are critically important, as it provides a route to improve the interpretability and reliability of HQML models, thus promoting greater confidence and being able to engage in safer and more responsible use of quantum-enhanced AI technology. Our code and experiments are open-sourced at: https://github.com/GitsSaikat/QuXAI