QMetric: Benchmarking Quantum Neural Networks Across Circuits, Features, and Training Dimensions

2025/06/30 by Silvie Illésová, Tomasz Rybotycki, Illésová, Silvie +3 · 5 citations
Computer Science · Materials Science · #Computational Physics (physics.comp-ph) #FOS: Physical sciences #Machine Learning in Materials Science #Neural Networks and Applications #Quantum Computing Algorithms and Architecture #Quantum Physics (quant-ph)

paper · pdf · doi:10.48550/arxiv.2506.23765

openalex publication_date 2025/06/30 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28

Abstract

As hybrid quantum-classical models gain traction in machine learning, there is a growing need for tools that assess their effectiveness beyond raw accuracy. We present QMetric, a Python package offering a suite of interpretable metrics to evaluate quantum circuit expressibility, feature representations, and training dynamics. QMetric quantifies key aspects such as circuit fidelity, entanglement entropy, barren plateau risk, and training stability. The package integrates with Qiskit and PyTorch, and is demonstrated via a case study on binary MNIST classification comparing classical and quantum-enhanced models. Code, plots, and a reproducible environment are available on GitLab.

Citations

• Benchmarking gate-based quantum devices via certification of qubit von Neumann measurements
• Optimization Strategies for Variational Quantum Algorithms in Noisy Landscapes
• Numerical Optimization Strategies for the Variational Hamiltonian Ansatz in Noisy Quantum Environments
• Experimental study of multiple-shot unitary channels discrimination using the IBM Q computers
• Qracle: A Graph-Neural-Network-based Parameter Initializer for Variational Quantum Eigensolvers
• Efficient Quantum Chemistry Calculations on Noisy Quantum Hardware
• Transformation-free generation of a quasi-diabatic representation from the state-average orbital-optimized variational quantum eigensolver
• Deep-Q Learning with Hybrid Quantum Neural Network on Solving Maze Problems
• Feature Map for Quantum Data in Classification
• On the generalization of learning algorithms that do not converge
• Scientific Machine Learning Benchmarks
• VQE Method: A Short Survey and Recent Developments
• Quantum versus Classical Generative Modelling in Finance
• Operator Entanglement in Local Quantum Circuits I: Chaotic Dual-Unitary Circuits
• Quantum Kitchen Sinks: An algorithm for machine learning on near-term quantum computers
• Diverse Neural Network Learns True Target Functions
• On the Computational Efficiency of Training Neural Networks
• An introduction to quantum machine learning
• The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]

Cited by

• Reliable Optimization Under Noise in Quantum Variational Algorithms
• From Classical to Hybrid: A Practical Framework for Quantum-Enhanced Learning
• Statistical Benchmarking of Optimization Methods for Variational Quantum Eigensolver under Quantum Noise
• On the Differential Topology of Expressivity of Parameterized Quantum Circuits
• On the Importance of Fundamental Properties in Quantum-Classical Machine Learning Models

Related

• Q-gen: A Parameterized Quantum Circuit Generator
• QDataset: Quantum Datasets for Machine Learning
• Addressing Temporal Variations in Qubit Quality Metrics for\n Parameterized Quantum Circuits
• Comprehensive Survey of QML: From Data Analysis to Algorithmic Advancements
• QuFoundry: Generating Data with Quantum Properties for Quantum Machine Learning Utility