Mutual information maximizing quantum generative adversarial networks

TL;DR

This paper introduces InfoQGAN, a hybrid quantum-classical generative model that uses mutual information maximization to improve feature control and reduce mode collapse in quantum generative adversarial networks, demonstrating promising results on synthetic and real datasets.

Contribution

The paper presents a novel InfoQGAN architecture integrating mutual information maximization into QGANs, enhancing feature disentanglement and training stability in quantum generative models.

Findings

Effective mitigation of mode collapse in quantum generative models

Enhanced feature disentanglement in quantum data generation

Improved data augmentation performance with controlled features

Abstract

One of the most promising applications in the era of Noisy Intermediate-Scale Quantum (NISQ) computing is quantum generative adversarial networks (QGANs), which offer significant quantum advantages over classical machine learning in various domains. However, QGANs suffer from mode collapse and lack explicit control over the features of generated outputs. To overcome these limitations, we propose InfoQGAN, a novel quantum-classical hybrid generative adversarial network that integrates the principles of InfoGAN with a QGAN architecture. Our approach employs a variational quantum circuit for data generation, a classical discriminator, and a Mutual Information Neural Estimator (MINE) to explicitly optimize the mutual information between latent codes and generated samples. Numerical simulations on synthetic 2D distributions and Iris dataset augmentation demonstrate that InfoQGAN effectively mitigates mode collapse while achieving robust feature disentanglement in the quantum generator. By leveraging these advantages, InfoQGAN not only enhances training stability but also improves data augmentation performance through controlled feature generation. These results highlight the potential of InfoQGAN as a foundational approach for advancing quantum generative modeling in the NISQ era.