Alert button
Picture for Dimitrios Gunopoulos

Dimitrios Gunopoulos

Alert button

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

Add code
Bookmark button
Alert button
Dec 08, 2020
Raghav Kansal, Javier Duarte, Breno Orzari, Thiago Tomei, Maurizio Pierini, Mary Touranakou, Jean-Roch Vlimant, Dimitrios Gunopoulos

Figure 1 for Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
Figure 2 for Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
Figure 3 for Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
Figure 4 for Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics

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.

* 9 pages, 4 figures, 4 tables, To appear in Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020) 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon