PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions
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...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2024
|
| Online Access: | https://hdl.handle.net/1721.1/155807 |
| _version_ | 1824458123723669504 |
|---|---|
| author | Semlani, Yash Relan, Mihir Ramesh, Krithik |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Semlani, Yash Relan, Mihir Ramesh, Krithik |
| author_sort | Semlani, Yash |
| collection | MIT |
| description | 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 |
| first_indexed | 2024-09-23T11:50:03Z |
| format | Article |
| id | mit-1721.1/155807 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:20:53Z |
| publishDate | 2024 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1558072025-01-04T05:43:41Z PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions Semlani, Yash Relan, Mihir Ramesh, Krithik Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 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 2024-07-30T19:31:15Z 2024-07-30T19:31:15Z 2024-07-26 2024-07-28T03:25:36Z Article http://purl.org/eprint/type/JournalArticle 1029-8479 https://hdl.handle.net/1721.1/155807 Semlani, Y., Relan, M. & Ramesh, K. PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions. J. High Energ. Phys. 2024, 247 (2024). PUBLISHER_CC en 10.1007/jhep07(2024)247 Journal of High Energy Physics Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer Science and Business Media LLC Springer Berlin Heidelberg |
| spellingShingle | Semlani, Yash Relan, Mihir Ramesh, Krithik PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions |
| 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 |
| url | https://hdl.handle.net/1721.1/155807 |
| work_keys_str_mv | AT semlaniyash pcnadeeplearningapproachtojettaggingutilizingnovelgraphconstructionmethodsandchebyshevgraphconvolutions AT relanmihir pcnadeeplearningapproachtojettaggingutilizingnovelgraphconstructionmethodsandchebyshevgraphconvolutions AT rameshkrithik pcnadeeplearningapproachtojettaggingutilizingnovelgraphconstructionmethodsandchebyshevgraphconvolutions |