# Selectively increasing the diversity of GAN-generated samples

arXiv: https://arxiv.org/abs/2207.01561 · HTML: https://mlsanity.com/paper/2207.01561/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 16 of 16)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (2019)
- [CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks](https://mlsanity.com/paper/1712.10321/) (2017)
- [Diversity-Sensitive Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1901.09024/) (2019)
- [Particle Cloud Generation with Message Passing Generative Adversarial Networks](https://mlsanity.com/paper/2106.11535/) (2021)
- [DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network](https://mlsanity.com/paper/2103.07893/) (2021)
- [End-to-end Sinkhorn Autoencoder with Noise Generator](https://mlsanity.com/paper/2006.06704/) (2020)
- [Fast cosmic web simulations with generative adversarial networks](https://mlsanity.com/paper/1801.09070/) (2018)
- [BinGAN: Learning Compact Binary Descriptors with a Regularized GAN](https://mlsanity.com/paper/1806.06778/) (2018)
- [Data Augmentation using Generative Adversarial Networks (GANs) for GAN-based Detection of Pneumonia and COVID-19 in Chest X-ray Images](https://mlsanity.com/paper/2006.03622/) (2020)

## Built on by (most cited first, 9 of 9)

- [Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN](https://mlsanity.com/paper/2406.03233/) (2024)
- [Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN](https://mlsanity.com/paper/2306.13606/) (2023)
- [Epistemic Generative Adversarial Networks](https://mlsanity.com/paper/2603.18348/) (2026)
- [Inverse Autoregressive Flows for Zero Degree Calorimeter fast simulation](https://mlsanity.com/paper/2512.20346/) (2025)
- [Even Faster Simulations with Flow Matching: A Study of Zero Degree Calorimeter Responses](https://mlsanity.com/paper/2507.18811/) (2025)
- [Particle physics DL-simulation with control over generated data properties](https://mlsanity.com/paper/2405.14049/) (2024)
- [Deep Generative Models for Proton Zero Degree Calorimeter Simulations in ALICE, CERN](https://mlsanity.com/paper/2406.03263/) (2024)
- [ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts](https://mlsanity.com/paper/2508.20991/) (2025)
- [Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation](https://mlsanity.com/paper/2608.12795/) (2026)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are powerful models able to synthesize data samples closely resembling the distribution of real data, yet the diversity of those generated samples is limited due to the so-called mode collapse phenomenon observed in GANs. Especially prone to mode collapse are conditional GANs, which tend to ignore the input noise vector and focus on the conditional information. Recent methods proposed to mitigate this limitation increase the diversity of generated samples, yet they reduce the performance of the models when similarity of samples is required. To address this shortcoming, we propose a novel method to selectively increase the diversity of GAN-generated samples. By adding a simple, yet effective regularization to the training loss function we encourage the generator to discover new data modes for inputs related to diverse outputs while generating consistent samples for the remaining ones. More precisely, we maximise the ratio of distances between generated images and input latent vectors scaling the effect according to the diversity of samples for a given conditional input. We show the superiority of our method in a synthetic benchmark as well as a real-life scenario of simulating data from the Zero Degree Calorimeter of ALICE experiment in LHC, CERN.