PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions

Abstract Jet tagging is a classification problem in high-energy physics experiments that aims to identify the collimated sprays of subatomic particles, jets, from particle collisions and ‘tag’ them to their emitter particle. Advances in jet tagging present opportunities for searches of new physics b...

Full description

Saved in:
Bibliographic Details
Main Authors: Yash Semlani, Mihir Relan, Krithik Ramesh
Format: Article
Language:English
Published: SpringerOpen 2024-07-01
Series:Journal of High Energy Physics
Subjects:
Online Access:https://doi.org/10.1007/JHEP07(2024)247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203624600240128
author Yash Semlani
Mihir Relan
Krithik Ramesh
author_facet Yash Semlani
Mihir Relan
Krithik Ramesh
author_sort Yash Semlani
collection DOAJ
description Abstract Jet tagging is a classification problem in high-energy physics experiments that aims to identify the collimated sprays of subatomic particles, jets, from particle collisions and ‘tag’ them to their emitter particle. Advances in jet tagging present opportunities for searches of new physics beyond the Standard Model. Current approaches use deep learning to uncover hidden patterns in complex collision data. However, the representation of jets as inputs to a deep learning model have been varied, and often, informative features are withheld from models. In this study, we propose a graph-based representation of a jet that encodes the most information possible. To learn best from this representation, we design Particle Chebyshev Network (PCN), a graph neural network (GNN) using Chebyshev graph convolutions (ChebConv). ChebConv has been demonstrated as an effective alternative to classical graph convolutions in GNNs and has yet to be explored in jet tagging. PCN achieves a substantial improvement in accuracy over existing taggers and opens the door to future studies into graph-based representations of jets and ChebConv layers in high-energy physics experiments. Code is available at https://github.com/YVSemlani/PCN-Jet-Tagging
format Article
id doaj-art-61a80f4efdc640d0a60f7af55ac39b2b
institution OA Journals
issn 1029-8479
language English
publishDate 2024-07-01
publisher SpringerOpen
record_format Article
series Journal of High Energy Physics
spelling doaj-art-61a80f4efdc640d0a60f7af55ac39b2b2025-08-20T02:11:28ZengSpringerOpenJournal of High Energy Physics1029-84792024-07-012024711510.1007/JHEP07(2024)247PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutionsYash Semlani0Mihir Relan1Krithik Ramesh2University of North Carolina at Chapel HillJohns Hopkins UniversityMassachusetts Institute of TechnologyAbstract Jet tagging is a classification problem in high-energy physics experiments that aims to identify the collimated sprays of subatomic particles, jets, from particle collisions and ‘tag’ them to their emitter particle. Advances in jet tagging present opportunities for searches of new physics beyond the Standard Model. Current approaches use deep learning to uncover hidden patterns in complex collision data. However, the representation of jets as inputs to a deep learning model have been varied, and often, informative features are withheld from models. In this study, we propose a graph-based representation of a jet that encodes the most information possible. To learn best from this representation, we design Particle Chebyshev Network (PCN), a graph neural network (GNN) using Chebyshev graph convolutions (ChebConv). ChebConv has been demonstrated as an effective alternative to classical graph convolutions in GNNs and has yet to be explored in jet tagging. PCN achieves a substantial improvement in accuracy over existing taggers and opens the door to future studies into graph-based representations of jets and ChebConv layers in high-energy physics experiments. Code is available at https://github.com/YVSemlani/PCN-Jet-Tagginghttps://doi.org/10.1007/JHEP07(2024)247Jets and Jet SubstructureTop Quark
spellingShingle Yash Semlani
Mihir Relan
Krithik Ramesh
PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions
Journal of High Energy Physics
Jets and Jet Substructure
Top Quark
title PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions
title_full PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions
title_fullStr PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions
title_full_unstemmed PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions
title_short PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions
title_sort pcn a deep learning approach to jet tagging utilizing novel graph construction methods and chebyshev graph convolutions
topic Jets and Jet Substructure
Top Quark
url https://doi.org/10.1007/JHEP07(2024)247
work_keys_str_mv AT yashsemlani pcnadeeplearningapproachtojettaggingutilizingnovelgraphconstructionmethodsandchebyshevgraphconvolutions
AT mihirrelan pcnadeeplearningapproachtojettaggingutilizingnovelgraphconstructionmethodsandchebyshevgraphconvolutions
AT krithikramesh pcnadeeplearningapproachtojettaggingutilizingnovelgraphconstructionmethodsandchebyshevgraphconvolutions