JEDI-net: a jet identification algorithm based on interaction networks

Moreno, Eric A.; Cerri, Olmo; Duarte, Javier M.; Newman, Harvey B.; Nguyen, Thong Q.; Periwal, Avikar; Pierini, Maurizio; Serikova, Aidana; Spiropulu, Maria; Vlimant, Jean-Roch

doi:10.1140/epjc/s10052-020-7608-4

Title: JEDI-net: a jet identification algorithm based on interaction networks

Abstract

Abstract We investigate the performance of a jet identification algorithm based on interaction networks (JEDI-net) to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The jet dynamics are described as a set of one-to-one interactions between the jet constituents. Based on a representation learned from these interactions, the jet is associated to one of the considered categories. Unlike other architectures, the JEDI-net models achieve their performance without special handling of the sparse input jet representation, extensive pre-processing, particle ordering, or specific assumptions regarding the underlying detector geometry. The presented models give better results with less model parameters, offering interesting prospects for LHC applications.

Authors:: Moreno, Eric A.; Cerri, Olmo; Duarte, Javier M.; Newman, Harvey B.; Nguyen, Thong Q.; Periwal, Avikar; Pierini, Maurizio; Serikova, Aidana; Spiropulu, Maria; Vlimant, Jean-Roch

Publication Date:: Sat Jan 25 00:00:00 EST 2020

Research Org.:: Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)

Sponsoring Org.:: USDOE Office of Science (SC), High Energy Physics (HEP)

OSTI Identifier:: 1619359

Alternate Identifier(s):: OSTI ID: 1561543

Report Number(s):: arXiv:1908.05318; FERMILAB-PUB-19-360-PPD
Journal ID: ISSN 1434-6044; 58; PII: 7608

Grant/Contract Number:: AC02-07CH11359; SC0011925

Resource Type:: Published Article

Journal Name:: European Physical Journal. C, Particles and Fields

Additional Journal Information:: Journal Name: European Physical Journal. C, Particles and Fields Journal Volume: 80 Journal Issue: 1; Journal ID: ISSN 1434-6044

Publisher:: Springer Science + Business Media

Country of Publication:: Germany

Language:: English

Subject:: 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats


                    Moreno, Eric A., Cerri, Olmo, Duarte, Javier M., Newman, Harvey B., Nguyen, Thong Q., Periwal, Avikar, Pierini, Maurizio, Serikova, Aidana, Spiropulu, Maria, and Vlimant, Jean-Roch. JEDI-net: a jet identification algorithm based on interaction networks.  Germany: N. p., 2020. 
Web.  doi:10.1140/epjc/s10052-020-7608-4.

Copy to clipboard


                    Moreno, Eric A., Cerri, Olmo, Duarte, Javier M., Newman, Harvey B., Nguyen, Thong Q., Periwal, Avikar, Pierini, Maurizio, Serikova, Aidana, Spiropulu, Maria, & Vlimant, Jean-Roch. JEDI-net: a jet identification algorithm based on interaction networks.  Germany.  https://doi.org/10.1140/epjc/s10052-020-7608-4

Copy to clipboard


                    Moreno, Eric A., Cerri, Olmo, Duarte, Javier M., Newman, Harvey B., Nguyen, Thong Q., Periwal, Avikar, Pierini, Maurizio, Serikova, Aidana, Spiropulu, Maria, and Vlimant, Jean-Roch. Sat .  
"JEDI-net: a jet identification algorithm based on interaction networks".  Germany.  https://doi.org/10.1140/epjc/s10052-020-7608-4.

Copy to clipboard


                    
@article{osti_1619359,

  title        = {JEDI-net: a jet identification algorithm based on interaction networks},

  author       = {Moreno, Eric A. and Cerri, Olmo and Duarte, Javier M. and Newman, Harvey B. and Nguyen, Thong Q. and Periwal, Avikar and Pierini, Maurizio and Serikova, Aidana and Spiropulu, Maria and Vlimant, Jean-Roch},

  abstractNote = {Abstract We investigate the performance of a jet identification algorithm based on interaction networks (JEDI-net) to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The jet dynamics are described as a set of one-to-one interactions between the jet constituents. Based on a representation learned from these interactions, the jet is associated to one of the considered categories. Unlike other architectures, the JEDI-net models achieve their performance without special handling of the sparse input jet representation, extensive pre-processing, particle ordering, or specific assumptions regarding the underlying detector geometry. The presented models give better results with less model parameters, offering interesting prospects for LHC applications.},

  doi          = {10.1140/epjc/s10052-020-7608-4},

  journal      = {European Physical Journal. C, Particles and Fields},

  number       = 1,

  volume       = 80,

  place        = {Germany},

  year         = {Sat Jan 25 00:00:00 EST 2020},

  month        = {Sat Jan 25 00:00:00 EST 2020}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Publisher's Version of Record
https://doi.org/10.1140/epjc/s10052-020-7608-4

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 60 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

HLS4ML LHC Jet dataset (150 particles)
dataset, January 2020

Pierini, Maurizio; Duarte, Javier Mauricio; Tran, Nhan
Zenodo
DOI: 10.5281/zenodo.3602260

The anti- k _t jet clustering algorithm
journal, April 2008

Cacciari, Matteo; Salam, Gavin P.; Soyez, Gregory
Journal of High Energy Physics, Vol. 2008, Issue 04
DOI: 10.1088/1126-6708/2008/04/063

Pulling out all the tops with computer vision and deep learning
journal, October 2018

Macaluso, Sebastian; Shih, David
Journal of High Energy Physics, Vol. 2018, Issue 10
DOI: 10.1007/JHEP10(2018)121

Learning representations of irregular particle-detector geometry with distance-weighted graph networks
journal, July 2019

Qasim, Shah Rukh; Kieseler, Jan; Iiyama, Yutaro
The European Physical Journal C, Vol. 79, Issue 7
DOI: 10.1140/epjc/s10052-019-7113-9

Deep-learned Top Tagging with a Lorentz Layer
journal, January 2018

Butter, Anja; Kasieczka, Gregor; Plehn, Tilman
SciPost Physics, Vol. 5, Issue 3
DOI: 10.21468/SciPostPhys.5.3.028

Fast inference of deep neural networks in FPGAs for particle physics
journal, July 2018

Duarte, J.; Han, S.; Harris, P.
Journal of Instrumentation, Vol. 13, Issue 07
DOI: 10.1088/1748-0221/13/07/P07027

Energy flow networks: deep sets for particle jets
journal, January 2019

Komiske, Patrick T.; Metodiev, Eric M.; Thaler, Jesse
Journal of High Energy Physics, Vol. 2019, Issue 1
DOI: 10.1007/JHEP01(2019)121

HLS4ML LHC Jet dataset (30 particles)
dataset, January 2020

Pierini, Maurizio; Duarte, Javier Mauricio; Tran, Nhan
Zenodo
DOI: 10.5281/zenodo.3601436

Longitudinally-invariant k⊥-clustering algorithms for hadron-hadron collisions
journal, September 1993

Catani, S.; Dokshitzer, Yu. L.; Seymour, M. H.
Nuclear Physics B, Vol. 406, Issue 1-2
DOI: 10.1016/0550-3213(93)90166-M

Graph Neural Networks for IceCube Signal Classification
conference, December 2018

Choma, Nicholas; Bruna, Joan; Monti, Federico
2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)
DOI: 10.1109/ICMLA.2018.00064

The Machine Learning landscape of top taggers
journal, January 2019

Kasieczka, Gregor; Plehn, Tilman; Butter, Anja
SciPost Physics, Vol. 7, Issue 1
DOI: 10.21468/SciPostPhys.7.1.014

Jet-images — deep learning edition
journal, July 2016

de Oliveira, Luke; Kagan, Michael; Mackey, Lester
Journal of High Energy Physics, Vol. 2016, Issue 7
DOI: 10.1007/JHEP07(2016)069

Deep-learning top taggers or the end of QCD?
journal, May 2017

Kasieczka, Gregor; Plehn, Tilman; Russell, Michael
Journal of High Energy Physics, Vol. 2017, Issue 5
DOI: 10.1007/JHEP05(2017)006

Deep learning in color: towards automated quark/gluon jet discrimination
journal, January 2017

Komiske, Patrick T.; Metodiev, Eric M.; Schwartz, Matthew D.
Journal of High Energy Physics, Vol. 2017, Issue 1
DOI: 10.1007/JHEP01(2017)110

FastJet user manual: (for version 3.0.2)
journal, March 2012

Cacciari, Matteo; Salam, Gavin P.; Soyez, Gregory
The European Physical Journal C, Vol. 72, Issue 3
DOI: 10.1140/epjc/s10052-012-1896-2

Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
journal, April 1980

Fukushima, Kunihiko
Biological Cybernetics, Vol. 36, Issue 4
DOI: 10.1007/BF00344251

Novel jet observables from machine learning
journal, March 2018

Datta, Kaustuv; Larkoski, Andrew J.
Journal of High Energy Physics, Vol. 2018, Issue 3
DOI: 10.1007/JHEP03(2018)086

Identifying boosted objects with N-subjettiness
journal, March 2011

Thaler, Jesse; Van Tilburg, Ken
Journal of High Energy Physics, Vol. 2011, Issue 3
DOI: 10.1007/JHEP03(2011)015

Jet flavor classification in high-energy physics with deep neural networks
journal, December 2016

Guest, Daniel; Collado, Julian; Baldi, Pierre
Physical Review D, Vol. 94, Issue 11
DOI: 10.1103/PhysRevD.94.112002

Probing stop pair production at the LHC with graph neural networks
journal, August 2019

Abdughani, Murat; Ren, Jie; Wu, Lei
Journal of High Energy Physics, Vol. 2019, Issue 8
DOI: 10.1007/JHEP08(2019)055

Recursive Neural Networks in Quark/Gluon Tagging
journal, June 2018

Cheng, Taoli
Computing and Software for Big Science, Vol. 2, Issue 1
DOI: 10.1007/s41781-018-0007-y

Image Processing, Computer Vision, and Deep Learning: new approaches to the analysis and physics interpretation of LHC events
journal, October 2016

Schwartzman, A.; Kagan, M.; Mackey, L.
Journal of Physics: Conference Series, Vol. 762
DOI: 10.1088/1742-6596/762/1/012035

Pileup mitigation at the Large Hadron Collider with graph neural networks
journal, July 2019

Arjona Martínez, J.; Cerri, O.; Spiropulu, M.
The European Physical Journal Plus, Vol. 134, Issue 7
DOI: 10.1140/epjp/i2019-12710-3

QCD-aware recursive neural networks for jet physics
journal, January 2019

Louppe, Gilles; Cho, Kyunghyun; Becot, Cyril
Journal of High Energy Physics, Vol. 2019, Issue 1
DOI: 10.1007/JHEP01(2019)057

HLS4ML LHC Jet dataset (50 particles)
dataset, January 2020

Pierini, Maurizio; Duarte, Javier Mauricio; Tran, Nhan
Zenodo
DOI: 10.5281/zenodo.3601443

Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms.
journal, September 1962

Orbach, J.
Archives of General Psychiatry, Vol. 7, Issue 3
DOI: 10.1001/archpsyc.1962.01720030064010

Better jet clustering algorithms
journal, August 1997

Dokshitzer, Yu. L.; Leder, G. D.; Moretti, S.
Journal of High Energy Physics, Vol. 1997, Issue 08
DOI: 10.1088/1126-6708/1997/08/001

The importance of calorimetry for highly-boosted jet substructure
journal, January 2018

Coleman, E.; Freytsis, M.; Hinzmann, A.
Journal of Instrumentation, Vol. 13, Issue 01
DOI: 10.1088/1748-0221/13/01/T01003

HLS4ML LHC Jet dataset (100 particles)
dataset, January 2020

Pierini, Maurizio; Duarte, Javier Mauricio; Tran, Nhan
Zenodo
DOI: 10.5281/zenodo.3602254

Similar Records in DOE PAGES and OSTI.GOV collections:

Interaction networks for the identification of boosted H → $$b\overline b$$ decays

Journal Article Moreno, Eric A. ; Nguyen, Thong Q. ; Vlimant, Jean-Roch ; ... - Physical Review. D.

We develop an algorithm based on an interaction network to identify high-transverse-momentum Higgs bosons decaying to bottom quark-antiquark pairs and distinguish them from ordinary jets that reflect the configurations of quarks and gluons at short distances. The algorithm's inputs are features of the reconstructed charged particles in a jet and the secondary vertices associated with them. Describing the jet shower as a combination of particle-to-particle and particle-to-vertex interactions, the model is trained to learn a jet representation on which the classification problem is optimized. The algorithm is trained on simulated samples of realistic LHC collisions, released by the CMS Collaborationmore »« less
Cited by 29
https://doi.org/10.1103/PhysRevD.102.012010
A detailed study of interpretability of deep neural network based top taggers

Journal Article Khot, Ayush ; Neubauer, Mark S. ; Roy, Avik - Machine Learning: Science and Technology

Abstract Recent developments in the methods of explainable AI (XAI) allow researchers to explore the inner workings of deep neural networks (DNNs), revealing crucial information about input-output relationships and realizing how data connects with machine learning models. In this paper we explore interpretability of DNN models designed to identify jets coming from top quark decay in high energy proton-proton collisions at the Large Hadron Collider (LHC). We review a subset of existing top tagger models and explore different quantitative methods to identify which features play the most important roles in identifying the top jets. We also investigate how and whymore »« less
https://doi.org/10.1088/2632-2153/ace0a1
MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

Journal Article Pata, Joosep ; Duarte, Javier ; Vlimant, Jean-Roch ; ... - European Physical Journal. C, Particles and Fields

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum. In view of the planned high-luminosity upgrade of the CERN Large Hadron Collider (LHC), it is necessary to revisit existing reconstruction algorithms and ensure that both the physics and computational performance are sufficient in an environment with many simultaneous proton–proton interactions (pileup). Machine learning may offer a prospect for computationally efficient event reconstruction that is well-suited to heterogeneous computing platforms,more »« less
https://doi.org/10.1140/epjc/s10052-021-09158-w

Full Text Available
B-jet and c-jet identification with Neural Networks as well as combination of multivariate analyses for the search for of multivariate analyses for the search for single top-quark production

Technical Report Renz, Manuel ; /Karlsruhe U., EKP

In the first part of this diploma thesis, the current version of the KIT Flavor Separator, a neural network which is able to distinguish between tagged b-quark jets and tagged c/light-quark jets, is presented. In comparison with previous versions four new input variables are utilized and new Monte Carlo samples with a larger number of simulated events are used for the training of the neural network. It is illustrated that the output of the neural network is continuously distributed between 1 and -1, whereas b-quark jets accumulate at 1, however, c-quark jets and light-quark jets have outputs next to -1.more »« less
https://doi.org/10.2172/957074

Full Text Available
Identification of hadronic tau lepton decays using a deep neural network

Journal Article Tumasyan, A. ; Adam, W. ; Andrejkovic, J. W. ; ... - Journal of Instrumentation

A new algorithm is presented to discriminate reconstructed hadronic decays of tau leptons (τh) that originate from genuine tau leptons in the CMS detector against τh candidates that originate from quark or gluon jets, electrons, or muons. The algorithm inputs information from all reconstructed particles in the vicinity of a τh candidate and employs a deep neural network with convolutional layers to efficiently process the inputs. This algorithm leads to a significantly improved performance compared with the previously used one. For example, the efficiency for a genuine τh to pass the discriminator against jets increases by 10–30% for a givenmore »« less
https://doi.org/10.1088/1748-0221/17/07/p07023

Full Text Available

Similar Records

Title: JEDI-net: a jet identification algorithm based on interaction networks

Abstract

Citation Formats

HLS4ML LHC Jet dataset (150 particles) dataset, January 2020

The anti- k t jet clustering algorithm journal, April 2008

Pulling out all the tops with computer vision and deep learning journal, October 2018

Learning representations of irregular particle-detector geometry with distance-weighted graph networks journal, July 2019

Deep-learned Top Tagging with a Lorentz Layer journal, January 2018

Fast inference of deep neural networks in FPGAs for particle physics journal, July 2018

Energy flow networks: deep sets for particle jets journal, January 2019

HLS4ML LHC Jet dataset (30 particles) dataset, January 2020

Longitudinally-invariant k⊥-clustering algorithms for hadron-hadron collisions journal, September 1993

Graph Neural Networks for IceCube Signal Classification conference, December 2018

The Machine Learning landscape of top taggers journal, January 2019

Jet-images — deep learning edition journal, July 2016

Deep-learning top taggers or the end of QCD? journal, May 2017

Deep learning in color: towards automated quark/gluon jet discrimination journal, January 2017

FastJet user manual: (for version 3.0.2) journal, March 2012

Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position journal, April 1980

Novel jet observables from machine learning journal, March 2018

Identifying boosted objects with N-subjettiness journal, March 2011

Jet flavor classification in high-energy physics with deep neural networks journal, December 2016

Probing stop pair production at the LHC with graph neural networks journal, August 2019

Recursive Neural Networks in Quark/Gluon Tagging journal, June 2018

Image Processing, Computer Vision, and Deep Learning: new approaches to the analysis and physics interpretation of LHC events journal, October 2016

Pileup mitigation at the Large Hadron Collider with graph neural networks journal, July 2019

QCD-aware recursive neural networks for jet physics journal, January 2019

HLS4ML LHC Jet dataset (50 particles) dataset, January 2020

Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms. journal, September 1962

Better jet clustering algorithms journal, August 1997

The importance of calorimetry for highly-boosted jet substructure journal, January 2018

HLS4ML LHC Jet dataset (100 particles) dataset, January 2020

HLS4ML LHC Jet dataset (150 particles)
dataset, January 2020

The anti- k _t jet clustering algorithm
journal, April 2008

Pulling out all the tops with computer vision and deep learning
journal, October 2018

Learning representations of irregular particle-detector geometry with distance-weighted graph networks
journal, July 2019

Deep-learned Top Tagging with a Lorentz Layer
journal, January 2018

Fast inference of deep neural networks in FPGAs for particle physics
journal, July 2018

Energy flow networks: deep sets for particle jets
journal, January 2019

HLS4ML LHC Jet dataset (30 particles)
dataset, January 2020

Longitudinally-invariant k⊥-clustering algorithms for hadron-hadron collisions
journal, September 1993

Graph Neural Networks for IceCube Signal Classification
conference, December 2018

The Machine Learning landscape of top taggers
journal, January 2019

Jet-images — deep learning edition
journal, July 2016

Deep-learning top taggers or the end of QCD?
journal, May 2017

Deep learning in color: towards automated quark/gluon jet discrimination
journal, January 2017

FastJet user manual: (for version 3.0.2)
journal, March 2012

Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
journal, April 1980

Novel jet observables from machine learning
journal, March 2018

Identifying boosted objects with N-subjettiness
journal, March 2011

Jet flavor classification in high-energy physics with deep neural networks
journal, December 2016

Probing stop pair production at the LHC with graph neural networks
journal, August 2019

Recursive Neural Networks in Quark/Gluon Tagging
journal, June 2018

Image Processing, Computer Vision, and Deep Learning: new approaches to the analysis and physics interpretation of LHC events
journal, October 2016

Pileup mitigation at the Large Hadron Collider with graph neural networks
journal, July 2019

QCD-aware recursive neural networks for jet physics
journal, January 2019

HLS4ML LHC Jet dataset (50 particles)
dataset, January 2020

Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms.
journal, September 1962

Better jet clustering algorithms
journal, August 1997

The importance of calorimetry for highly-boosted jet substructure
journal, January 2018

HLS4ML LHC Jet dataset (100 particles)
dataset, January 2020