VAE-QWGAN: Addressing Mode Collapse in Quantum GANs via Autoencoding Priors

TL;DR

This paper introduces VAE-QWGAN, a hybrid quantum-classical generative model that mitigates mode collapse in quantum GANs by integrating a Variational AutoEncoder with a Quantum Wasserstein GAN, improving diversity and quality of generated images.

Contribution

The work presents a novel hybrid quantum-classical model combining VAE and QWGAN to address mode collapse in quantum GANs, with a learned GMM prior for better data generation.

Findings

VAE-QWGAN outperforms existing QGANs in diversity and quality metrics.

The model effectively mitigates mode collapse in quantum generative models.

Experimental results on MNIST datasets demonstrate significant improvements.

Abstract

Recent proposals for quantum generative adversarial networks (GANs) suffer from the issue of mode collapse, analogous to classical GANs, wherein the distribution learnt by the GAN fails to capture the high mode complexities of the target distribution. Mode collapse can arise due to the use of uninformed prior distributions in the generative learning task. To alleviate the issue of mode collapse for quantum GANs, this work presents a novel \textbf{hybrid quantum-classical generative model}, the VAE-QWGAN, which combines the strengths of a classical Variational AutoEncoder (VAE) with a hybrid Quantum Wasserstein GAN (QWGAN). The VAE-QWGAN fuses the VAE decoder and QWGAN generator into a single quantum model, and utilizes the VAE encoder for data-dependant latent vector sampling during training. This in turn, enhances the diversity and quality of generated images. To generate new data from the trained model at inference, we sample from a Gaussian mixture model (GMM) prior that is learnt on the latent vectors generated during training. We conduct extensive experiments for image generation QGANs on MNIST/Fashion-MNIST datasets and compute a range of metrics that measure the diversity and quality of generated samples. We show that VAE-QWGAN demonstrates significant improvement over existing QGAN approaches.