Evaluating quantum generative models via imbalanced data classification benchmarks

TL;DR

This paper systematically evaluates quantum generative models for imbalanced data classification using explainable AI techniques on synthetic data from diverse real-world datasets, benchmarking their performance and analyzing their suitability.

Contribution

It introduces a novel framework combining explainable AI with quantum data generation to assess model behavior across various complex, imbalanced datasets.

Findings

Quantum-generated data shows comparable classification performance to classical methods.

Certain data complexities influence the effectiveness of quantum generative models.

The approach helps identify problem characteristics suitable for quantum-classical hybrid models.

Abstract

A limited set of tools exist for assessing whether the behavior of quantum machine learning models diverges from conventional models, outside of abstract or theoretical settings. We present a systematic application of explainable artificial intelligence techniques to analyze synthetic data generated from a hybrid quantum-classical neural network adapted from twenty different real-world data sets, including solar flares, cardiac arrhythmia, and speech data. Each of these data sets exhibits varying degrees of complexity and class imbalance. We benchmark the quantum-generated data relative to state-of-the-art methods for mitigating class imbalance for associated classification tasks. We leverage this approach to elucidate the qualities of a problem that make it more or less likely to be amenable to a hybrid quantum-classical generative model.