# Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder

arXiv: https://arxiv.org/abs/2002.02112 · HTML: https://mlsanity.com/paper/2002.02112/

## Key facts

- Cited by 13 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 6 Feb 2020.

## Built on by (most cited first, 13 of 13)

- [Projected GANs Converge Faster](https://mlsanity.com/paper/2111.01007/) (2021)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [Balanced Training for Sparse GANs](https://mlsanity.com/paper/2302.14670/) (2023)
- [Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparison](https://mlsanity.com/paper/2103.09316/) (2021)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance](https://mlsanity.com/paper/2203.02770/) (2022)
- [SSLChange: A Self-supervised Change Detection Framework Based on Domain Adaptation](https://mlsanity.com/paper/2405.18224/) (2024)
- [Fine-tuning of Pre-trained End-to-end Speech Recognition with Generative Adversarial Networks](https://mlsanity.com/paper/2103.13329/) (2021)
- [SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2104.12977/) (2021)
- [ARTEMIS: Using GANs with Multiple Discriminators to Generate Art](https://mlsanity.com/paper/2311.08278/) (2023)
- [TAEGAN: Generating Synthetic Tabular Data For Data Augmentation](https://mlsanity.com/paper/2410.01933/) (2024)
- [ParaColorizer: Realistic Image Colorization using Parallel Generative Networks](https://mlsanity.com/paper/2208.08295/) (2022)
- [HP-GAN: Harnessing pretrained networks for GAN improvement with FakeTwins and discriminator consistency](https://mlsanity.com/paper/2602.03039/) (2026)

## Abstract (arXiv)

We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE). We guarantee the stable training of the generator by preventing the faster convergence of the discriminator at early epochs. Furthermore, we balance between the generator and the discriminator at early epochs and thus maintain the stabilized training of GANs. We apply Unbalanced GANs to well known public datasets and find that Unbalanced GANs reduce mode collapses. We also show that Unbalanced GANs outperform ordinary GANs in terms of stabilized learning, faster convergence and better image quality at early epochs.