Quantum and Classical Kernels Applied to Classification of Unbalanced Datasets

• Fernando Mondragon-Sampedro ^[1] ; Diego Alvarez-Estevez ^[1]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
• Localización: Proceedings XoveTIC 2025: Impulsando el talento científico / coord. por Manuel Lagos Rodríguez, Hilda Romero-Velo, Álvaro Leitao , Javier Pereira-Loureiro , Manuel Penedo , 2026, ISBN 978-84-9749-925-5, págs. 139-144
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • This work investigates quantum kernel methods for classification on unbalanceddatasets. The study considers the effect of techniques commonly used in classical machinelearning, such as kernel centering and cost-sensitive learning, when applied to quantum mod-els. Experiments are conducted on five datasets, including MNIST-1D, the real-world datasetGlass6, and synthetic datasets tailored for quantum classifiers. Results indicate that quantumkernel methods can address unbalanced classification tasks albeit none of the techniques stud-ied showed a statistically significant improvement of the scoring metrics. Results also highlightthe influence of hyperparameterization and in particular, quantum bandwidth is identified as acritical hyperparameter for the performance of quantum models.