Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learning
arXiv:2301.09138 · doi:10.1007/s42484-025-00254-8
Abstract
Methods of artificial intelligence (AI) and especially machine learning (ML) have been growing ever more complex, and at the same time have more and more impact on people's lives. This leads to explainable AI (XAI) manifesting itself as an important research field that helps humans to better comprehend ML systems. In parallel, quantum machine learning (QML) is emerging with the ongoing improvement of quantum computing hardware combined with its increasing availability via cloud services. QML enables quantum-enhanced ML in which quantum mechanics is exploited to facilitate ML tasks, typically in the form of quantum-classical hybrid algorithms that combine quantum and classical resources. Quantum gates constitute the building blocks of gate-based quantum hardware and form circuits that can be used for quantum computations. For QML applications, quantum circuits are typically parameterized and their parameters are optimized classically such that a suitably defined objective function is minimized. Inspired by XAI, we raise the question of the explainability of such circuits by quantifying the importance of (groups of) gates for specific goals. To this end, we apply the well-established concept of Shapley values. The resulting attributions can be interpreted as explanations for why a specific circuit works well for a given task, improving the understanding of how to construct parameterized (or variational) quantum circuits, and fostering their human interpretability in general. An experimental evaluation on simulators and two superconducting quantum hardware devices demonstrates the benefits of the proposed framework for classification, generative modeling, transpilation, and optimization. Furthermore, our results shed some light on the role of specific gates in popular QML approaches.
41 pages, 27 figures, 3 tables
References in corpus (42)
- Quantum Computing in the NISQ era and beyond
- Quantum Machine Learning
- Variational Quantum Algorithms
- Supervised learning with quantum enhanced feature spaces
- Quantum fingerprinting
- Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
- From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
- The effect of data encoding on the expressive power of variational quantum machine learning models
- Power of data in quantum machine learning
- Validating quantum computers using randomized model circuits
- Quantum optimization using variational algorithms on near-term quantum devices
- Connecting ansatz expressibility to gradient magnitudes and barren plateaus
- A rigorous and robust quantum speed-up in supervised machine learning
- Global entanglement in multiparticle systems
- Generalization in quantum machine learning from few training data
- Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
- Quantum-enhanced machine learning
- Decoherence benchmarking of superconducting qubits
- Random Quantum Circuits are Approximate 2-designs
- Scalable mitigation of measurement errors on quantum computers
- Is quantum advantage the right goal for quantum machine learning?
- Detecting crosstalk errors in quantum information processors
- What limits the simulation of quantum computers?
- Quantum circuit architecture search for variational quantum algorithms
- Supervised quantum machine learning models are kernel methods
- Capacity and quantum geometry of parametrized quantum circuits
- Modelling and Simulating the Noisy Behaviour of Near-term Quantum Computers
- Quantum games: a review of the history, current state, and interpretation
- Efficient measure for the expressivity of variational quantum algorithms
- Expressibility of the alternating layered ansatz for quantum computation
- Pulse-efficient circuit transpilation for quantum applications on cross-resonance-based hardware
- Learning quantum data with the quantum Earth Mover's distance
- Adaptive pruning-based optimization of parameterized quantum circuits
- On the Interpretability of Quantum Neural Networks
- A Survey on Quantum Reinforcement Learning
- Analysing Neural Network Topologies: a Game Theoretic Approach
- Unsupervised quantum machine learning for fraud detection
- Representation of binary classification trees with binary features by quantum circuits
- Estimation of pure quantum states in high dimension at the limit of quantum accuracy through complex optimization and statistical inference
- Quantum Circuit Evolution on NISQ Devices
- Quantum circuit debugging and sensitivity analysis via local inversions
- Shapley Values with Uncertain Value Functions