# Alleviation of Gradient Exploding in GANs: Fake Can Be Real

arXiv: https://arxiv.org/abs/1912.12485 · HTML: https://mlsanity.com/paper/1912.12485/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [HairCLIP: Design Your Hair by Text and Reference Image](https://mlsanity.com/paper/2112.05142/) (2021)
- [Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis](https://mlsanity.com/paper/2104.05703/) (2021)
- [Anomaly Detection in Additive Manufacturing Processes using Supervised Classification with Imbalanced Sensor Data based on Generative Adversarial Network](https://mlsanity.com/paper/2210.17274/) (2022)
- [3D Brain and Heart Volume Generative Models: A Survey](https://mlsanity.com/paper/2210.05952/) (2022)
- [Disentanglement in a GAN for Unconditional Speech Synthesis](https://mlsanity.com/paper/2307.01673/) (2023)
- [GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models](https://mlsanity.com/paper/2210.05271/) (2022)
- [CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization](https://mlsanity.com/paper/2404.00521/) (2024)
- [From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs](https://mlsanity.com/paper/2605.30014/) (2026)

## Abstract (arXiv)

In order to alleviate the notorious mode collapse phenomenon in generative adversarial networks (GANs), we propose a novel training method of GANs in which certain fake samples are considered as real ones during the training process. This strategy can reduce the gradient value that generator receives in the region where gradient exploding happens. We show the process of an unbalanced generation and a vicious circle issue resulted from gradient exploding in practical training, which explains the instability of GANs. We also theoretically prove that gradient exploding can be alleviated by penalizing the difference between discriminator outputs and fake-as-real consideration for very close real and fake samples. Accordingly, Fake-As-Real GAN (FARGAN) is proposed with a more stable training process and a more faithful generated distribution. Experiments on different datasets verify our theoretical analysis.