# LSTM-QGAN: Scalable NISQ Generative Adversarial Network

arXiv: https://arxiv.org/abs/2409.02212 · HTML: https://mlsanity.com/paper/2409.02212/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2024.

## Built on by (most cited first, 4 of 4)

- [Quantum Long Short-term Memory with Differentiable Architecture Search](https://mlsanity.com/paper/2508.14955/) (2025)
- [Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation](https://mlsanity.com/paper/2606.24932/) (2026)
- [Self-Modulating Quantum Fast-Weight Programmers for Efficient Adaptive Sequential Learning](https://mlsanity.com/paper/2606.24933/) (2026)
- [On the Generalization Limits of Quantum Generative Adversarial Networks with Pure State Generators](https://mlsanity.com/paper/2508.09844/) (2025)

## Abstract (arXiv)

Current quantum generative adversarial networks (QGANs) still struggle with practical-sized data. First, many QGANs use principal component analysis (PCA) for dimension reduction, which, as our studies reveal, can diminish the QGAN's effectiveness. Second, methods that segment inputs into smaller patches processed by multiple generators face scalability issues. In this work, we propose LSTM-QGAN, a QGAN architecture that eliminates PCA preprocessing and integrates quantum long short-term memory (QLSTM) to ensure scalable performance. Our experiments show that LSTM-QGAN significantly enhances both performance and scalability over state-of-the-art QGAN models, with visual data improvements, reduced Frechet Inception Distance scores, and reductions of 5x in qubit counts, 5x in single-qubit gates, and 12x in two-qubit gates.