# Mode Regularized Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1612.02136 · HTML: https://mlsanity.com/paper/1612.02136/

## Key facts

- Cited by 123 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2016.

## Built on by (most cited first, 30 of 123)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](https://mlsanity.com/paper/2208.09392/) (2022)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Aligning Language Models with Preferences through f-divergence Minimization](https://mlsanity.com/paper/2302.08215/) (2023)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Deep Generative Learning via Schr"odinger Bridge](https://mlsanity.com/paper/2106.10410/) (2021)
- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [Neural Conservation Laws: A Divergence-Free Perspective](https://mlsanity.com/paper/2210.01741/) (2022)
- [DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers](https://mlsanity.com/paper/2204.12997/) (2022)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision](https://mlsanity.com/paper/2412.09262/) (2024)
- [Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances](https://mlsanity.com/paper/2111.00418/) (2021)
- [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)
- [Autoregressive Models in Vision: A Survey](https://mlsanity.com/paper/2411.05902/) (2024)
- [Diffusion Model-Augmented Behavioral Cloning](https://mlsanity.com/paper/2302.13335/) (2023)
- [3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generation](https://mlsanity.com/paper/2412.13059/) (2024)
- [Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction](https://mlsanity.com/paper/2504.15266/) (2025)
- [Diagnosing and Fixing Manifold Overfitting in Deep Generative Models](https://mlsanity.com/paper/2204.07172/) (2022)
- [Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme](https://mlsanity.com/paper/2110.14439/) (2021)
- [FloMo: Tractable Motion Prediction with Normalizing Flows](https://mlsanity.com/paper/2103.03614/) (2021)
- [Conditional GANs with Auxiliary Discriminative Classifier](https://mlsanity.com/paper/2107.10060/) (2021)
- [Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling](https://mlsanity.com/paper/2407.02446/) (2024)
- [EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Models](https://mlsanity.com/paper/2303.05656/) (2023)
- [A Survey on Quality Metrics for Text-to-Image Generation](https://mlsanity.com/paper/2403.11821/) (2024)
- [Conditional Frechet Inception Distance](https://mlsanity.com/paper/2103.11521/) (2021)
- [A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science](https://mlsanity.com/paper/2403.12636/) (2024)
- [Rates of convergence for density estimation with generative adversarial networks](https://mlsanity.com/paper/2102.00199/) (2021)

## Abstract (arXiv)

Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN models. We also show that our regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training and thus providing a unified solution to the missing modes problem.