QGAN-based data augmentation for hybrid quantum-classical neural networks

TL;DR

This paper introduces a quantum generative adversarial network (QGAN) framework for data augmentation in hybrid quantum-classical neural networks, demonstrating improved efficiency and accuracy on the MNIST dataset.

Contribution

It presents novel strategies for quantum data augmentation using QGANs, enhancing the performance of hybrid quantum-classical neural networks with fewer parameters.

Findings

QGAN outperforms traditional augmentation methods and classical GANs on MNIST.

QGAN achieves similar performance to baseline DCGAN with half the parameters.

Quantum data augmentation improves HQCNN accuracy and efficiency.

Abstract

Quantum neural networks converge faster and achieve higher accuracy than classical models. However, data augmentation in quantum machine learning remains underexplored. To tackle data scarcity, we integrate quantum generative adversarial networks (QGANs) with hybrid quantum-classical neural networks (HQCNNs) to develop an augmentation framework. We propose two strategies: a general approach to enhance data processing and classification across HQCNNs, and a customized strategy that dynamically generates samples tailored to the HQCNN's performance on specific data categories, improving its ability to learn from complex datasets. Simulation experiments on the MNIST dataset demonstrate that QGAN outperforms traditional data augmentation methods and classical GANs. Compared to baseline DCGAN, QGAN achieves comparable performance with half the parameters, balancing efficiency and effectiveness. This suggests that QGANs can simplify models and generate high-quality data, enhancing HQCNN accuracy and performance. These findings pave the way for applying quantum data augmentation techniques in machine learning.