# Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics

arXiv: https://arxiv.org/abs/2012.00173 · HTML: https://mlsanity.com/paper/2012.00173/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [A Living Review of Machine Learning for Particle Physics](https://mlsanity.com/paper/2102.02770/) (2021)
- [CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows](https://mlsanity.com/paper/2106.05285/) (2021)
- [MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks](https://mlsanity.com/paper/2101.08578/) (2021)
- [Deep Generative Models for Detector Signature Simulation: A Taxonomic Review](https://mlsanity.com/paper/2312.09597/) (2023)
- [New directions for surrogate models and differentiable programming for High Energy Physics detector simulation](https://mlsanity.com/paper/2203.08806/) (2022)
- [Lorentz group equivariant autoencoders](https://mlsanity.com/paper/2212.07347/) (2022)
- [Latent Space Refinement for Deep Generative Models](https://mlsanity.com/paper/2106.00792/) (2021)
- [Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics](https://mlsanity.com/paper/2104.03408/) (2021)
- [Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders](https://mlsanity.com/paper/2203.00520/) (2022)
- [Shared Data and Algorithms for Deep Learning in Fundamental Physics](https://mlsanity.com/paper/2107.00656/) (2021)
- [Versatile Energy-Based Probabilistic Models for High Energy Physics](https://mlsanity.com/paper/2302.00695/) (2023)

## Abstract (arXiv)

We develop a graph generative adversarial network to generate sparse data sets like those produced at the CERN Large Hadron Collider (LHC). We demonstrate this approach by training on and generating sparse representations of MNIST handwritten digit images and jets of particles in proton-proton collisions like those at the LHC. We find the model successfully generates sparse MNIST digits and particle jet data. We quantify agreement between real and generated data with a graph-based Fr'echet Inception distance, and the particle and jet feature-level 1-Wasserstein distance for the MNIST and jet datasets respectively.