A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification

TL;DR

This paper introduces a versatile variational quantum kernel framework designed for complex, high-dimensional real-world data classification, demonstrating competitive accuracy with classical methods through extensive benchmarking.

Contribution

It presents a new algorithmic framework with resource-efficient ansätze and a parameter scaling technique, enabling effective quantum kernel application on diverse real-world datasets.

Findings

Quantum kernels achieve competitive accuracy with classical RBF kernels.

The framework performs well across tabular, image, time series, and graph data.

Resource-efficient ansätze improve scalability and convergence.

Abstract

Quantum kernel methods are a promising branch of quantum machine learning, yet their effectiveness on diverse, high-dimensional, real-world data remains unverified. Current research has largely been limited to low-dimensional or synthetic datasets, preventing a thorough evaluation of their potential. To address this gap, we developed an algorithmic framework for variational quantum kernels utilizing resource-efficient ans\"atze for complex classification tasks and introduced a parameter scaling technique to accelerate convergence. We conducted a comprehensive benchmark of this framework on eight challenging, real-world and high-dimensional datasets covering tabular, image, time series, and graph data. Our results show that the proposed quantum kernels demonstrate competitive classification accuracy compared to standard classical kernels in classical simulation, such as the radial basis function (RBF) kernel. This work demonstrates that properly designed quantum kernels can function as versatile, high-performance tools, laying a foundation for quantum-enhanced applications in real-world machine learning. Further research is needed to fully assess the practical performance of quantum methods.