A Caltech Library Service

Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors

Ju, Xiangyang and Farrell, Steven and Calafiura, Paolo and Murnane, Daniel and Gray, Lindsey and Klijnsma, Thomas and Pedro, Kevin and Cerati, Giuseppe and Kowalkowski, Jim and Perdue, Gabriel and Spentzouris, Panagiotis and Tran, Nhan and Vlimant, Jean-Roch and Zlokapa, Alexander and Pata, Joosep and Spiropulu, Maria and An, Sitong and Aurisano, Adam and Hewes, Jeremy and Tsaris, Aristeidis and Terao, Kasuhiro and Usher, Tracy (2020) Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in high energy collisions and recorded with complex detector systems. Two critical applications are the reconstruction of charged particle trajectories in tracking detectors and the reconstruction of particle showers in calorimeters. These two problems have unique challenges and characteristics, but both have high dimensionality, high degree of sparsity, and complex geometric layouts. Graph Neural Networks (GNNs) are a relatively new class of deep learning architectures which can deal with such data effectively, allowing scientists to incorporate domain knowledge in a graph structure and learn powerful representations leveraging that structure to identify patterns of interest. In this work we demonstrate the applicability of GNNs to these two diverse particle reconstruction problems.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Vlimant, Jean-Roch0000-0002-9705-101X
Zlokapa, Alexander0000-0002-4153-8646
Spiropulu, Maria0000-0001-8172-7081
Additional Information:We are grateful to Javier Duarte, Phillip Harris, and Jim Hirschauer for the useful discussions. This research was supported in part by the Office of Science, Office of High Energy Physics, of the US Department of Energy under Contracts No. DE-AC02-05CH11231 and No. DE-AC02-07CH11359. This research used resources of the National Energy Research Scientific Computing Center (NERSC), a U.S. Department of Energy Office of Science User Facility operated under Contract No. DE-AC02-05CH11231. Part of this work was conducted at "iBanks", the AI GPU cluster at Caltech. We acknowledge NVIDIA, SuperMicro and the Kavli Foundation for their support of "iBanks". L.G., T.K., K.P., and N.T. are partially supported by Fermilab LDRD L2019.017: "Graph Neural Networks for Accelerating Calorimetry and Event Reconstruction". S.A. is supported by the Marie Skłodowska-Curie Innovative Training Network Fellowship of the European Commission’s Horizon 2020 Programme under contract number 765710 INSIGHTS.
Funding AgencyGrant Number
Department of Energy (DOE)DE-AC02-05CH11231
Department of Energy (DOE)DE-AC02-07CH11359
Department of Energy (DOE)DE-AC02- 05CH11231
Kavli FoundationUNSPECIFIED
FermilabLDRD L2019.017
Marie Curie Fellowship765710 INSIGHTS
Record Number:CaltechAUTHORS:20200423-161944499
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:102762
Deposited By: Joy Painter
Deposited On:23 Apr 2020 23:31
Last Modified:10 Feb 2021 18:36

Repository Staff Only: item control page