# MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation

arXiv: https://arxiv.org/abs/1805.02481 · HTML: https://mlsanity.com/paper/1805.02481/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 7 May 2018.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 14 of 14)

- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [A* Sampling](https://mlsanity.com/paper/1411.0030/) (2014)
- [BEGAN: Boundary Equilibrium Generative Adversarial Networks](https://mlsanity.com/paper/1703.10717/) (2017)
- [Stability](https://mlsanity.com/paper/1310.0150/) (2013)
- [Multi-Agent Diverse Generative Adversarial Networks](https://mlsanity.com/paper/1704.02906/) (2017)
- [Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.04357/) (2016)
- [AdaGAN: Boosting Generative Models](https://mlsanity.com/paper/1701.02386/) (2017)
- [On Convergence and Stability of GANs](https://mlsanity.com/paper/1705.07215/) (2017)
- [Multi-Generator Generative Adversarial Nets](https://mlsanity.com/paper/1708.02556/) (2017)
- [Class-Splitting Generative Adversarial Networks](https://mlsanity.com/paper/1709.07359/) (2017)

## Built on by (most cited first, 15 of 15)

- [A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2503.07137/) (2025)
- [Linear, or Non-Linear, That is the Question!](https://mlsanity.com/paper/2111.07265/) (2021)
- [MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators](https://mlsanity.com/paper/2107.07260/) (2021)
- [Multi-student Diffusion Distillation for Better One-step Generators](https://mlsanity.com/paper/2410.23274/) (2024)
- [Integration of Mixture of Experts and Multimodal Generative AI in Internet of Vehicles: A Survey](https://mlsanity.com/paper/2404.16356/) (2024)
- [Over-the-Air Design of GAN Training for mmWave MIMO Channel Estimation](https://mlsanity.com/paper/2205.12445/) (2022)
- [Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis](https://mlsanity.com/paper/2503.02152/) (2025)
- [Spatial-Temporal Mixture-of-Graph-Experts for Multi-Type Crime Prediction](https://mlsanity.com/paper/2409.15764/) (2024)
- [Text-to-3D Generation using Jensen-Shannon Score Distillation](https://mlsanity.com/paper/2503.10660/) (2025)
- [N-BEATS-MOE: N-BEATS with a Mixture-of-Experts Layer for Heterogeneous Time Series Forecasting](https://mlsanity.com/paper/2508.07490/) (2025)
- [VARGAN: Variance Enforcing Network Enhanced GAN](https://mlsanity.com/paper/2109.02117/) (2021)
- [ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts](https://mlsanity.com/paper/2508.20991/) (2025)
- [Enhanced Mixture 3D CGAN for Completion and Generation of 3D Objects](https://mlsanity.com/paper/2602.08046/) (2026)
- [FaceMoE: Mixture of Experts for Low-Resolution Face Recognition](https://mlsanity.com/paper/2606.32040/) (2026)
- [AuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance](https://mlsanity.com/paper/2610.11792/) (2026)

## Abstract (arXiv)

Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images. However, they often struggle in learning complex underlying modalities in a given dataset, resulting in poor-quality generated images. To mitigate this problem, we present a novel approach called mixture of experts GAN (MEGAN), an ensemble approach of multiple generator networks. Each generator network in MEGAN specializes in generating images with a particular subset of modalities, e.g., an image class. Instead of incorporating a separate step of handcrafted clustering of multiple modalities, our proposed model is trained through an end-to-end learning of multiple generators via gating networks, which is responsible for choosing the appropriate generator network for a given condition. We adopt the categorical reparameterization trick for a categorical decision to be made in selecting a generator while maintaining the flow of the gradients. We demonstrate that individual generators learn different and salient subparts of the data and achieve a multiscale structural similarity (MS-SSIM) score of 0.2470 for CelebA and a competitive unsupervised inception score of 8.33 in CIFAR-10.