QuXAI：混合量子机器学习模型的可解释性工具

QuXAI: Explainers for Hybrid Quantum Machine Learning Models

May 15, 2025

作者: Saikat Barua, Mostafizur Rahman, Shehenaz Khaled, Md Jafor Sadek, Rafiul Islam, Shahnewaz Siddique

cs.AI

摘要

混合量子-经典机器学习（HQML）模型的出现为计算智能开辟了新视野，但其固有的复杂性往往导致黑箱行为，削弱了应用中的透明度和可靠性。尽管量子系统的可解释人工智能（XAI）仍处于起步阶段，但在为采用量子特征编码后接经典学习的HQML架构设计的全局与局部解释方法上，存在显著的研究空白。本文聚焦这一空白，引入了基于Q-MEDLEY的QuXAI框架，用于解释这些混合系统中的特征重要性。我们的模型包括构建包含量子特征映射的HQML模型，运用Q-MEDLEY结合基于特征的推理，保留量子变换阶段并可视化所得归因。结果表明，Q-MEDLEY不仅能够识别HQML模型中有影响力的经典因素，还能有效分离噪声，并在经典验证环境中与现有XAI技术相媲美。消融研究进一步揭示了Q-MEDLEY复合结构的优势。本工作的意义重大，它为提升HQML模型的可解释性和可靠性提供了途径，从而增强了对量子增强AI技术的信心，促进了更安全、更负责任的使用。

English

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.