# Epistemic Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2603.18348 · HTML: https://mlsanity.com/paper/2603.18348/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)
- [Generative Multi-Adversarial Networks](https://mlsanity.com/paper/1611.01673/) (2016)
- [Multi-Agent Diverse Generative Adversarial Networks](https://mlsanity.com/paper/1704.02906/) (2017)
- [DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text](https://mlsanity.com/paper/1802.01345/) (2018)
- [Learn to Accumulate Evidence from All Training Samples: Theory and Practice](https://mlsanity.com/paper/2306.11113/) (2023)
- [Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation](https://mlsanity.com/paper/2412.00205/) (2024)
- [Random-Set Neural Networks (RS-NN)](https://mlsanity.com/paper/2307.05772/) (2023)
- [UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs](https://mlsanity.com/paper/2201.13279/) (2022)
- [Epistemic Deep Learning](https://mlsanity.com/paper/2206.07609/) (2022)
- [Visions of a generalized probability theory](https://mlsanity.com/paper/1810.10341/) (2018)
- [Selectively increasing the diversity of GAN-generated samples](https://mlsanity.com/paper/2207.01561/) (2022)
- [Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'](https://mlsanity.com/paper/2505.04950/) (2025)
- [Reasoning with random sets: An agenda for the future](https://mlsanity.com/paper/2401.09435/) (2023)
- [Epistemic Wrapping for Uncertainty Quantification](https://mlsanity.com/paper/2505.02277/) (2025)
- [Uncertainty-Aware Autonomous Vehicles: Predicting the Road Ahead](https://mlsanity.com/paper/2510.22680/) (2025)
- [A Belief Model for Conflicting and Uncertain Evidence -- Connecting Dempster-Shafer Theory and the Topology of Evidence](https://mlsanity.com/paper/2306.03532/) (2023)
- [VAE-QWGAN: Addressing Mode Collapse in Quantum GANs via Autoencoding Priors](https://mlsanity.com/paper/2409.10339/) (2024)
- [Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems](https://mlsanity.com/paper/2303.01268/) (2023)
- [Adaptive Input-image Normalization for Solving the Mode Collapse Problem in GAN-based X-ray Images](https://mlsanity.com/paper/2309.12245/) (2023)
- [FNBT: Full Negation Belief Transformation for Open-World Information Fusion Based on Dempster-Shafer Theory of Evidence](https://mlsanity.com/paper/2508.08075/) (2025)

## Built on by (most cited first, 4 of 4)

- [Random-Set Graph Neural Networks](https://mlsanity.com/paper/2605.11987/) (2026)
- [Credal Large Language Models for Semantic Commitment under Uncertainty](https://mlsanity.com/paper/2608.23244/) (2026)
- [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026)
- [XU-RS: Explaining Credal Width in Random-Set Language Models](https://mlsanity.com/paper/2609.37594/) (2026)

## Abstract (arXiv)

Generative models, particularly Generative Adversarial Networks (GANs), often suffer from a lack of output diversity, frequently generating similar samples rather than a wide range of variations. This paper introduces a novel generalization of the GAN loss function based on Dempster-Shafer theory of evidence, applied to both the generator and discriminator. Additionally, we propose an architectural enhancement to the generator that enables it to predict a mass function for each image pixel. This modification allows the model to quantify uncertainty in its outputs and leverage this uncertainty to produce more diverse and representative generations. Experimental evidence shows that our approach not only improves generation variability but also provides a principled framework for modeling and interpreting uncertainty in generative processes.