# Stabilizing Training of Generative Adversarial Networks through Regularization

arXiv: https://arxiv.org/abs/1705.09367 · HTML: https://mlsanity.com/paper/1705.09367/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2017.

## Built on by (most cited first, 30 of 118)

- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [Diffusion Adversarial Post-Training for One-Step Video Generation](https://mlsanity.com/paper/2501.08316/) (2025)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation](https://mlsanity.com/paper/2506.09350/) (2025)
- [Generative Models as Distributions of Functions](https://mlsanity.com/paper/2102.04776/) (2021)
- [Better Generative Replay for Continual Federated Learning](https://mlsanity.com/paper/2302.13001/) (2023)
- [Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning](https://mlsanity.com/paper/2005.14310/) (2020)
- [Text to Image Generation with Semantic-Spatial Aware GAN](https://mlsanity.com/paper/2104.00567/) (2021)
- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training](https://mlsanity.com/paper/2506.05301/) (2025)
- [Distribution Matching Distillation Meets Reinforcement Learning](https://mlsanity.com/paper/2511.13649/) (2025)
- [3D Shape Generation with Grid-based Implicit Functions](https://mlsanity.com/paper/2107.10607/) (2021)
- [Class-Balancing Diffusion Models](https://mlsanity.com/paper/2305.00562/) (2023)
- [Modeling Image Composition for Complex Scene Generation](https://mlsanity.com/paper/2206.00923/) (2022)
- [Context-Aware Layout to Image Generation with Enhanced Object Appearance](https://mlsanity.com/paper/2103.11897/) (2021)
- [Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport](https://mlsanity.com/paper/2305.14777/) (2023)
- [Achieving Fairness at No Utility Cost via Data Reweighing with Influence](https://mlsanity.com/paper/2202.00787/) (2022)
- [EigenGAN: Layer-Wise Eigen-Learning for GANs](https://mlsanity.com/paper/2104.12476/) (2021)
- [Free Lunch for Domain Adversarial Training: Environment Label Smoothing](https://mlsanity.com/paper/2302.00194/) (2023)
- [Statistical Analysis of Wasserstein Distributionally Robust Estimators](https://mlsanity.com/paper/2108.02120/) (2021)
- [Training Unbiased Diffusion Models From Biased Dataset](https://mlsanity.com/paper/2403.01189/) (2024)
- [Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport](https://mlsanity.com/paper/2402.05443/) (2024)
- [Disentangled Recurrent Wasserstein Autoencoder](https://mlsanity.com/paper/2101.07496/) (2021)
- [Representing 3D Shapes with Probabilistic Directed Distance Fields](https://mlsanity.com/paper/2112.05300/) (2021)
- [Diffusive Gibbs Sampling](https://mlsanity.com/paper/2402.03008/) (2024)
- [SpoofGAN: Synthetic Fingerprint Spoof Images](https://mlsanity.com/paper/2204.06498/) (2022)
- [Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning](https://mlsanity.com/paper/2006.16785/) (2020)
- [Manifold Learning Benefits GANs](https://mlsanity.com/paper/2112.12618/) (2021)

## Abstract (arXiv)

Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters. This fragility is in part due to a dimensional mismatch or non-overlapping support between the model distribution and the data distribution, causing their density ratio and the associated f-divergence to be undefined. We overcome this fundamental limitation and propose a new regularization approach with low computational cost that yields a stable GAN training procedure. We demonstrate the effectiveness of this regularizer across several architectures trained on common benchmark image generation tasks. Our regularization turns GAN models into reliable building blocks for deep learning.