View in EDS HTML Full Text PDF Full Text

Reconstructing particles in jets using set transformer and hypergraph prediction networks.

Saved in:
Bibliographic Details
Title: Reconstructing particles in jets using set transformer and hypergraph prediction networks.
Authors: Di Bello, Francesco Armando1 (AUTHOR), Dreyer, Etienne2 (AUTHOR), Ganguly, Sanmay3 (AUTHOR), Gross, Eilam2 (AUTHOR), Heinrich, Lukas4 (AUTHOR), Ivina, Anna2 (AUTHOR), Kado, Marumi5,6 (AUTHOR), Kakati, Nilotpal2 (AUTHOR) nilotpal.kakati@weizmann.ac.il, Santi, Lorenzo6 (AUTHOR), Shlomi, Jonathan2 (AUTHOR), Tusoni, Matteo6 (AUTHOR)
Source: European Physical Journal C -- Particles & Fields. Jul2023, Vol. 83 Issue 7, p1-18. 18p.
Subjects: Collisions (Nuclear physics), Hyperfragments, Detectors, Feynman diagrams
Abstract: The task of reconstructing particles from low-level detector response data to predict the set of final state particles in collision events represents a set-to-set prediction task requiring the use of multiple features and their correlations in the input data. We deploy three separate set-to-set neural network architectures to reconstruct particles in events containing a single jet in a fully-simulated calorimeter. Performance is evaluated in terms of particle reconstruction quality, properties regression, and jet-level metrics. The results demonstrate that such a high-dimensional end-to-end approach succeeds in surpassing basic parametric approaches in disentangling individual neutral particles inside of jets and optimizing the use of complementary detector information. In particular, the performance comparison favors a novel architecture based on learning hypergraph structure, HGPflow, which benefits from a physically-interpretable approach to particle reconstruction. [ABSTRACT FROM AUTHOR]
Copyright of European Physical Journal C -- Particles & Fields is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 169972095
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Reconstructing particles in jets using set transformer and hypergraph prediction networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Di+Bello%2C+Francesco+Armando%22">Di Bello, Francesco Armando</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dreyer%2C+Etienne%22">Dreyer, Etienne</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ganguly%2C+Sanmay%22">Ganguly, Sanmay</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gross%2C+Eilam%22">Gross, Eilam</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Heinrich%2C+Lukas%22">Heinrich, Lukas</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ivina%2C+Anna%22">Ivina, Anna</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kado%2C+Marumi%22">Kado, Marumi</searchLink><relatesTo>5,6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kakati%2C+Nilotpal%22">Kakati, Nilotpal</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> nilotpal.kakati@weizmann.ac.il</i><br /><searchLink fieldCode="AR" term="%22Santi%2C+Lorenzo%22">Santi, Lorenzo</searchLink><relatesTo>6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shlomi%2C+Jonathan%22">Shlomi, Jonathan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tusoni%2C+Matteo%22">Tusoni, Matteo</searchLink><relatesTo>6</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22European+Physical+Journal+C+--+Particles+%26+Fields%22">European Physical Journal C -- Particles & Fields</searchLink>. Jul2023, Vol. 83 Issue 7, p1-18. 18p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Collisions+%28Nuclear+physics%29%22">Collisions (Nuclear physics)</searchLink><br /><searchLink fieldCode="DE" term="%22Hyperfragments%22">Hyperfragments</searchLink><br /><searchLink fieldCode="DE" term="%22Detectors%22">Detectors</searchLink><br /><searchLink fieldCode="DE" term="%22Feynman+diagrams%22">Feynman diagrams</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The task of reconstructing particles from low-level detector response data to predict the set of final state particles in collision events represents a set-to-set prediction task requiring the use of multiple features and their correlations in the input data. We deploy three separate set-to-set neural network architectures to reconstruct particles in events containing a single jet in a fully-simulated calorimeter. Performance is evaluated in terms of particle reconstruction quality, properties regression, and jet-level metrics. The results demonstrate that such a high-dimensional end-to-end approach succeeds in surpassing basic parametric approaches in disentangling individual neutral particles inside of jets and optimizing the use of complementary detector information. In particular, the performance comparison favors a novel architecture based on learning hypergraph structure, HGPflow, which benefits from a physically-interpretable approach to particle reconstruction. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of European Physical Journal C -- Particles & Fields is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=169972095
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1140/epjc/s10052-023-11677-7
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 18
        StartPage: 1
    Subjects:
      – SubjectFull: Collisions (Nuclear physics)
        Type: general
      – SubjectFull: Hyperfragments
        Type: general
      – SubjectFull: Detectors
        Type: general
      – SubjectFull: Feynman diagrams
        Type: general
    Titles:
      – TitleFull: Reconstructing particles in jets using set transformer and hypergraph prediction networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Di Bello, Francesco Armando
      – PersonEntity:
          Name:
            NameFull: Dreyer, Etienne
      – PersonEntity:
          Name:
            NameFull: Ganguly, Sanmay
      – PersonEntity:
          Name:
            NameFull: Gross, Eilam
      – PersonEntity:
          Name:
            NameFull: Heinrich, Lukas
      – PersonEntity:
          Name:
            NameFull: Ivina, Anna
      – PersonEntity:
          Name:
            NameFull: Kado, Marumi
      – PersonEntity:
          Name:
            NameFull: Kakati, Nilotpal
      – PersonEntity:
          Name:
            NameFull: Santi, Lorenzo
      – PersonEntity:
          Name:
            NameFull: Shlomi, Jonathan
      – PersonEntity:
          Name:
            NameFull: Tusoni, Matteo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 14346044
          Numbering:
            – Type: volume
              Value: 83
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: European Physical Journal C -- Particles & Fields
              Type: main
ResultId 1