# VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

arXiv: https://arxiv.org/abs/1705.07761 · HTML: https://mlsanity.com/paper/1705.07761/

## Key facts

- Cited by 200 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2017.

## Built on by (most cited first, 30 of 200)

- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [Imitating Human Behaviour with Diffusion Models](https://mlsanity.com/paper/2301.10677/) (2023)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Mildly Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2206.04745/) (2022)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing](https://mlsanity.com/paper/2104.14754/) (2021)
- [STaSy: Score-based Tabular data Synthesis](https://mlsanity.com/paper/2210.04018/) (2022)
- [CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis](https://mlsanity.com/paper/2304.12654/) (2023)
- [Neural Conservation Laws: A Divergence-Free Perspective](https://mlsanity.com/paper/2210.01741/) (2022)
- [Synthetic Data -- what, why and how?](https://mlsanity.com/paper/2205.03257/) (2022)
- [DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers](https://mlsanity.com/paper/2204.12997/) (2022)
- [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](https://mlsanity.com/paper/2111.01118/) (2021)
- [VampNet: Music Generation via Masked Acoustic Token Modeling](https://mlsanity.com/paper/2307.04686/) (2023)
- [LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision](https://mlsanity.com/paper/2412.09262/) (2024)
- [Scalable Diffusion for Materials Generation](https://mlsanity.com/paper/2311.09235/) (2023)
- [P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision](https://mlsanity.com/paper/2205.02300/) (2022)
- [Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation](https://mlsanity.com/paper/2305.18470/) (2023)
- [On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence](https://mlsanity.com/paper/2207.04630/) (2022)
- [MissDiff: Training Diffusion Models on Tabular Data with Missing Values](https://mlsanity.com/paper/2307.00467/) (2023)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Semi-Parametric Neural Image Synthesis](https://mlsanity.com/paper/2204.11824/) (2022)
- [GATSBI: Generative Adversarial Training for Simulation-Based Inference](https://mlsanity.com/paper/2203.06481/) (2022)
- [Taming Mode Collapse in Score Distillation for Text-to-3D Generation](https://mlsanity.com/paper/2401.00909/) (2023)
- [Copula Flows for Synthetic Data Generation](https://mlsanity.com/paper/2101.00598/) (2021)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Dual Contrastive Loss and Attention for GANs](https://mlsanity.com/paper/2103.16748/) (2021)

## Abstract (arXiv)

Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part because they are prone to mode collapse, which means that they characterize only a few modes of the true distribution. To address this, we introduce VEEGAN, which features a reconstructor network, reversing the action of the generator by mapping from data to noise. Our training objective retains the original asymptotic consistency guarantee of GANs, and can be interpreted as a novel autoencoder loss over the noise. In sharp contrast to a traditional autoencoder over data points, VEEGAN does not require specifying a loss function over the data, but rather only over the representations, which are standard normal by assumption. On an extensive set of synthetic and real world image datasets, VEEGAN indeed resists mode collapsing to a far greater extent than other recent GAN variants, and produces more realistic samples.