Mutual information maximizing quantum generative adversarial networks

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.

11 pages, 7 figures

References in corpus (11)

• Quantum Machine Learning
• Quantum Circuit Learning
• An introduction to quantum machine learning
• Quantum Error Mitigation
• Quantum generative adversarial learning
• Practical Quantum Error Mitigation for Near-Future Applications
• Hybrid quantum-classical algorithms and quantum error mitigation
• Quantum generative adversarial networks
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Estimating Quantum Mutual Information Through a Quantum Neural Network
• Quantum Neural Estimation of Entropies