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

arXiv: https://arxiv.org/abs/2409.10339 · HTML: https://mlsanity.com/paper/2409.10339/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [The power of quantum neural networks](https://mlsanity.com/paper/2011.00027/) (2020)
- [Quantum Machine Learning](https://mlsanity.com/paper/1611.09347/) (2016)
- [VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning](https://mlsanity.com/paper/1705.07761/) (2017)
- [Noise-Induced Barren Plateaus in Variational Quantum Algorithms](https://mlsanity.com/paper/2007.14384/) (2020)
- [Quantum generative adversarial networks](https://mlsanity.com/paper/1804.08641/) (2018)
- [Experimental Quantum Generative Adversarial Networks for Image Generation](https://mlsanity.com/paper/2010.06201/) (2020)
- [On GANs and GMMs](https://mlsanity.com/paper/1805.12462/) (2018)
- [Recent Advances for Quantum Neural Networks in Generative Learning](https://mlsanity.com/paper/2206.03066/) (2022)
- [Conditional Flow Variational Autoencoders for Structured Sequence Prediction](https://mlsanity.com/paper/1908.09008/) (2019)
- [Diffusion Priors In Variational Autoencoders](https://mlsanity.com/paper/2106.15671/) (2021)
- [Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation](https://mlsanity.com/paper/2212.11614/) (2022)
- [Style-based quantum generative adversarial networks for Monte Carlo events](https://mlsanity.com/paper/2110.06933/) (2021)
- [MosaiQ: Quantum Generative Adversarial Networks for Image Generation on NISQ Computers](https://mlsanity.com/paper/2308.11096/) (2023)

## Built on by (most cited first, 2 of 2)

- [Epistemic Generative Adversarial Networks](https://mlsanity.com/paper/2603.18348/) (2026)
- [CoQui: A Coordinate-Conditioned Quantum Implicit Generative Adversarial Network for End-to-End Image Generation](https://mlsanity.com/paper/2608.11884/) (2026)

## Abstract (arXiv)

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 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.