Cargando…
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 colli...
| Autores principales: | , , , , , , , |
|---|---|
| Lenguaje: | eng |
| Publicado: |
2020
|
| Materias: | |
| Acceso en línea: | http://cds.cern.ch/record/2748371 |
| _version_ | 1780968973350731776 |
|---|---|
| author | Kansal, Raghav Duarte, Javier Orzari, Breno Tomei, Thiago Pierini, Maurizio Touranakou, Mary Vlimant, Jean-Roch Gunopulos, Dimitrios |
| author_facet | Kansal, Raghav Duarte, Javier Orzari, Breno Tomei, Thiago Pierini, Maurizio Touranakou, Mary Vlimant, Jean-Roch Gunopulos, Dimitrios |
| author_sort | Kansal, Raghav |
| collection | CERN |
| description | 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. |
| id | cern-2748371 |
| institution | Organización Europea para la Investigación Nuclear |
| language | eng |
| publishDate | 2020 |
| record_format | invenio |
| spelling | cern-27483712021-05-03T08:11:29Zhttp://cds.cern.ch/record/2748371engKansal, RaghavDuarte, JavierOrzari, BrenoTomei, ThiagoPierini, MaurizioTouranakou, MaryVlimant, Jean-RochGunopulos, DimitriosGraph Generative Adversarial Networks for Sparse Data Generation in High Energy Physicsphysics.comp-phOther Fields of Physicshep-phParticle Physics - Phenomenologyhep-exParticle Physics - Experimentcs.LGComputing and Computersphysics.data-anOther Fields of PhysicsWe 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.arXiv:2012.00173oai:cds.cern.ch:27483712020-11-30 |
| spellingShingle | physics.comp-ph Other Fields of Physics hep-ph Particle Physics - Phenomenology hep-ex Particle Physics - Experiment cs.LG Computing and Computers physics.data-an Other Fields of Physics Kansal, Raghav Duarte, Javier Orzari, Breno Tomei, Thiago Pierini, Maurizio Touranakou, Mary Vlimant, Jean-Roch Gunopulos, Dimitrios Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics |
| title | Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics |
| title_full | Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics |
| title_fullStr | Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics |
| title_full_unstemmed | Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics |
| title_short | Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics |
| title_sort | graph generative adversarial networks for sparse data generation in high energy physics |
| topic | physics.comp-ph Other Fields of Physics hep-ph Particle Physics - Phenomenology hep-ex Particle Physics - Experiment cs.LG Computing and Computers physics.data-an Other Fields of Physics |
| url | http://cds.cern.ch/record/2748371 |
| work_keys_str_mv | AT kansalraghav graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics AT duartejavier graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics AT orzaribreno graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics AT tomeithiago graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics AT pierinimaurizio graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics AT touranakoumary graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics AT vlimantjeanroch graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics AT gunopulosdimitrios graphgenerativeadversarialnetworksforsparsedatagenerationinhighenergyphysics |