# Variational Approaches for Auto-Encoding Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1706.04987 · HTML: https://mlsanity.com/paper/1706.04987/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2017.

## Built on by (most cited first, 30 of 52)

- [Parser-Free Virtual Try-on via Distilling Appearance Flows](https://mlsanity.com/paper/2103.04559/) (2021)
- [Style-Based Global Appearance Flow for Virtual Try-On](https://mlsanity.com/paper/2204.01046/) (2022)
- [DISSECT: Disentangled Simultaneous Explanations via Concept Traversals](https://mlsanity.com/paper/2105.15164/) (2021)
- [Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses](https://mlsanity.com/paper/2402.04013/) (2024)
- [Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design](https://mlsanity.com/paper/2302.02913/) (2023)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks](https://mlsanity.com/paper/2102.12033/) (2021)
- [OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup](https://mlsanity.com/paper/2301.00965/) (2023)
- [Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation](https://mlsanity.com/paper/2302.11294/) (2023)
- [Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images](https://mlsanity.com/paper/2208.03934/) (2022)
- [Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild](https://mlsanity.com/paper/2209.00642/) (2022)
- [StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis](https://mlsanity.com/paper/2104.07098/) (2021)
- [Training Generative Adversarial Networks in One Stage](https://mlsanity.com/paper/2103.00430/) (2021)
- [Semantic Perturbations with Normalizing Flows for Improved Generalization](https://mlsanity.com/paper/2108.07958/) (2021)
- [Inferential Wasserstein Generative Adversarial Networks](https://mlsanity.com/paper/2109.05652/) (2021)
- [Generating 3D Brain Tumor Regions in MRI using Vector-Quantization Generative Adversarial Networks](https://mlsanity.com/paper/2310.01251/) (2023)
- [Matching aggregate posteriors in the variational autoencoder](https://mlsanity.com/paper/2311.07693/) (2023)
- [Limb-Aware Virtual Try-On Network with Progressive Clothing Warping](https://mlsanity.com/paper/2503.14074/) (2025)
- [3D Brain and Heart Volume Generative Models: A Survey](https://mlsanity.com/paper/2210.05952/) (2022)
- [Sketch-based Creativity Support Tools using Deep Learning](https://mlsanity.com/paper/2111.09991/) (2021)
- [Improving Generalization via Uncertainty Driven Perturbations](https://mlsanity.com/paper/2202.05737/) (2022)
- [Generative augmentations for improved cardiac ultrasound segmentation using diffusion models](https://mlsanity.com/paper/2502.20100/) (2025)
- [Progressive Limb-Aware Virtual Try-On](https://mlsanity.com/paper/2503.12588/) (2025)
- [DINO: A Conditional Energy-Based GAN for Domain Translation](https://mlsanity.com/paper/2102.09281/) (2021)
- [CAGAN: Text-To-Image Generation with Combined Attention GANs](https://mlsanity.com/paper/2104.12663/) (2021)
- [Improved α-GAN architecture for generating 3D connected volumes with an application to radiosurgery treatment planning](https://mlsanity.com/paper/2207.11223/) (2022)
- [OT-Net: A Reusable Neural Optimal Transport Solver](https://mlsanity.com/paper/2306.08233/) (2023)
- [Learning Sequential Information in Task-based fMRI for Synthetic Data Augmentation](https://mlsanity.com/paper/2308.15564/) (2023)
- [Rapid Review of Generative AI in Smart Medical Applications](https://mlsanity.com/paper/2406.06627/) (2024)
- [Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancements](https://mlsanity.com/paper/2504.19197/) (2025)

## Abstract (arXiv)

Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the available training data. In this paper, we develop a principle upon which auto-encoders can be combined with generative adversarial networks by exploiting the hierarchical structure of the generative model. The underlying principle shows that variational inference can be used a basic tool for learning, but with the in- tractable likelihood replaced by a synthetic likelihood, and the unknown posterior distribution replaced by an implicit distribution; both synthetic likelihoods and implicit posterior distributions can be learned using discriminators. This allows us to develop a natural fusion of variational auto-encoders and generative adversarial networks, combining the best of both these methods. We describe a unified objective for optimization, discuss the constraints needed to guide learning, connect to the wide range of existing work, and use a battery of tests to systematically and quantitatively assess the performance of our method.