Track Seeding and Labelling with Embedded-space Graph Neural Networks
To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promising of these solutions, graph neural networks (GNN), process the event as a graph that connects track measurements (detec...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2020-06 |
---|---|
Hauptverfasser: | , , , , , , , , , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Choma, Nicholas Murnane, Daniel Ju, Xiangyang Calafiura, Paolo Conlon, Sean Farrell, Steven Prabhat Cerati, Giuseppe Gray, Lindsey Klijnsma, Thomas Kowalkowski, Jim Spentzouris, Panagiotis Jean-Roch Vlimant Spiropulu, Maria Aurisano, Adam Hewes, V Tsaris, Aristeidis Terao, Kazuhiro Usher, Tracy |
description | To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promising of these solutions, graph neural networks (GNN), process the event as a graph that connects track measurements (detector hits corresponding to nodes) with candidate line segments between the hits (corresponding to edges). Detector information can be associated with nodes and edges, enabling a GNN to propagate the embedded parameters around the graph and predict node-, edge- and graph-level observables. Previously, message-passing GNNs have shown success in predicting doublet likelihood, and we here report updates on the state-of-the-art architectures for this task. In addition, the Exa.TrkX project has investigated innovations in both graph construction, and embedded representations, in an effort to achieve fully learned end-to-end track finding. Hence, we present a suite of extensions to the original model, with encouraging results for hitgraph classification. In addition, we explore increased performance by constructing graphs from learned representations which contain non-linear metric structure, allowing for efficient clustering and neighborhood queries of data points. We demonstrate how this framework fits in with both traditional clustering pipelines, and GNN approaches. The embedded graphs feed into high-accuracy doublet and triplet classifiers, or can be used as an end-to-end track classifier by clustering in an embedded space. A set of post-processing methods improve performance with knowledge of the detector physics. Finally, we present numerical results on the TrackML particle tracking challenge dataset, where our framework shows favorable results in both seeding and track finding. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2419562364</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2419562364</sourcerecordid><originalsourceid>FETCH-proquest_journals_24195623643</originalsourceid><addsrcrecordid>eNqNissKgkAUQIcgSMp_GGg9oHfUah1Wi2iTe7k6t3xMajMj_n4GfUCrw-GcBfNAylDsI4AV861tgiCAZAdxLD2WZgbLlt-JVN09OXaKX7Egrb821a7i6asgpUgJO2BJ_GxwqPiNRoN6hpt609oNWz5QW_J_XLPtKc2OFzGY_j2SdXnTj6abUw5ReIgTkEkk_7s-H8M6RA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2419562364</pqid></control><display><type>article</type><title>Track Seeding and Labelling with Embedded-space Graph Neural Networks</title><source>Freely Accessible Journals</source><creator>Choma, Nicholas ; Murnane, Daniel ; Ju, Xiangyang ; Calafiura, Paolo ; Conlon, Sean ; Farrell, Steven ; Prabhat ; Cerati, Giuseppe ; Gray, Lindsey ; Klijnsma, Thomas ; Kowalkowski, Jim ; Spentzouris, Panagiotis ; Jean-Roch Vlimant ; Spiropulu, Maria ; Aurisano, Adam ; Hewes, V ; Tsaris, Aristeidis ; Terao, Kazuhiro ; Usher, Tracy</creator><creatorcontrib>Choma, Nicholas ; Murnane, Daniel ; Ju, Xiangyang ; Calafiura, Paolo ; Conlon, Sean ; Farrell, Steven ; Prabhat ; Cerati, Giuseppe ; Gray, Lindsey ; Klijnsma, Thomas ; Kowalkowski, Jim ; Spentzouris, Panagiotis ; Jean-Roch Vlimant ; Spiropulu, Maria ; Aurisano, Adam ; Hewes, V ; Tsaris, Aristeidis ; Terao, Kazuhiro ; Usher, Tracy</creatorcontrib><description>To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promising of these solutions, graph neural networks (GNN), process the event as a graph that connects track measurements (detector hits corresponding to nodes) with candidate line segments between the hits (corresponding to edges). Detector information can be associated with nodes and edges, enabling a GNN to propagate the embedded parameters around the graph and predict node-, edge- and graph-level observables. Previously, message-passing GNNs have shown success in predicting doublet likelihood, and we here report updates on the state-of-the-art architectures for this task. In addition, the Exa.TrkX project has investigated innovations in both graph construction, and embedded representations, in an effort to achieve fully learned end-to-end track finding. Hence, we present a suite of extensions to the original model, with encouraging results for hitgraph classification. In addition, we explore increased performance by constructing graphs from learned representations which contain non-linear metric structure, allowing for efficient clustering and neighborhood queries of data points. We demonstrate how this framework fits in with both traditional clustering pipelines, and GNN approaches. The embedded graphs feed into high-accuracy doublet and triplet classifiers, or can be used as an end-to-end track classifier by clustering in an embedded space. A set of post-processing methods improve performance with knowledge of the detector physics. Finally, we present numerical results on the TrackML particle tracking challenge dataset, where our framework shows favorable results in both seeding and track finding.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Classifiers ; Clustering ; Data points ; Graph neural networks ; Graph theory ; Graphical representations ; Graphs ; Machine learning ; Message passing ; Neural networks ; Nodes ; Particle tracking ; Performance enhancement ; Post-production processing ; Sensors</subject><ispartof>arXiv.org, 2020-06</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Choma, Nicholas</creatorcontrib><creatorcontrib>Murnane, Daniel</creatorcontrib><creatorcontrib>Ju, Xiangyang</creatorcontrib><creatorcontrib>Calafiura, Paolo</creatorcontrib><creatorcontrib>Conlon, Sean</creatorcontrib><creatorcontrib>Farrell, Steven</creatorcontrib><creatorcontrib>Prabhat</creatorcontrib><creatorcontrib>Cerati, Giuseppe</creatorcontrib><creatorcontrib>Gray, Lindsey</creatorcontrib><creatorcontrib>Klijnsma, Thomas</creatorcontrib><creatorcontrib>Kowalkowski, Jim</creatorcontrib><creatorcontrib>Spentzouris, Panagiotis</creatorcontrib><creatorcontrib>Jean-Roch Vlimant</creatorcontrib><creatorcontrib>Spiropulu, Maria</creatorcontrib><creatorcontrib>Aurisano, Adam</creatorcontrib><creatorcontrib>Hewes, V</creatorcontrib><creatorcontrib>Tsaris, Aristeidis</creatorcontrib><creatorcontrib>Terao, Kazuhiro</creatorcontrib><creatorcontrib>Usher, Tracy</creatorcontrib><title>Track Seeding and Labelling with Embedded-space Graph Neural Networks</title><title>arXiv.org</title><description>To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promising of these solutions, graph neural networks (GNN), process the event as a graph that connects track measurements (detector hits corresponding to nodes) with candidate line segments between the hits (corresponding to edges). Detector information can be associated with nodes and edges, enabling a GNN to propagate the embedded parameters around the graph and predict node-, edge- and graph-level observables. Previously, message-passing GNNs have shown success in predicting doublet likelihood, and we here report updates on the state-of-the-art architectures for this task. In addition, the Exa.TrkX project has investigated innovations in both graph construction, and embedded representations, in an effort to achieve fully learned end-to-end track finding. Hence, we present a suite of extensions to the original model, with encouraging results for hitgraph classification. In addition, we explore increased performance by constructing graphs from learned representations which contain non-linear metric structure, allowing for efficient clustering and neighborhood queries of data points. We demonstrate how this framework fits in with both traditional clustering pipelines, and GNN approaches. The embedded graphs feed into high-accuracy doublet and triplet classifiers, or can be used as an end-to-end track classifier by clustering in an embedded space. A set of post-processing methods improve performance with knowledge of the detector physics. Finally, we present numerical results on the TrackML particle tracking challenge dataset, where our framework shows favorable results in both seeding and track finding.</description><subject>Classifiers</subject><subject>Clustering</subject><subject>Data points</subject><subject>Graph neural networks</subject><subject>Graph theory</subject><subject>Graphical representations</subject><subject>Graphs</subject><subject>Machine learning</subject><subject>Message passing</subject><subject>Neural networks</subject><subject>Nodes</subject><subject>Particle tracking</subject><subject>Performance enhancement</subject><subject>Post-production processing</subject><subject>Sensors</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNissKgkAUQIcgSMp_GGg9oHfUah1Wi2iTe7k6t3xMajMj_n4GfUCrw-GcBfNAylDsI4AV861tgiCAZAdxLD2WZgbLlt-JVN09OXaKX7Egrb821a7i6asgpUgJO2BJ_GxwqPiNRoN6hpt609oNWz5QW_J_XLPtKc2OFzGY_j2SdXnTj6abUw5ReIgTkEkk_7s-H8M6RA</recordid><startdate>20200630</startdate><enddate>20200630</enddate><creator>Choma, Nicholas</creator><creator>Murnane, Daniel</creator><creator>Ju, Xiangyang</creator><creator>Calafiura, Paolo</creator><creator>Conlon, Sean</creator><creator>Farrell, Steven</creator><creator>Prabhat</creator><creator>Cerati, Giuseppe</creator><creator>Gray, Lindsey</creator><creator>Klijnsma, Thomas</creator><creator>Kowalkowski, Jim</creator><creator>Spentzouris, Panagiotis</creator><creator>Jean-Roch Vlimant</creator><creator>Spiropulu, Maria</creator><creator>Aurisano, Adam</creator><creator>Hewes, V</creator><creator>Tsaris, Aristeidis</creator><creator>Terao, Kazuhiro</creator><creator>Usher, Tracy</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200630</creationdate><title>Track Seeding and Labelling with Embedded-space Graph Neural Networks</title><author>Choma, Nicholas ; Murnane, Daniel ; Ju, Xiangyang ; Calafiura, Paolo ; Conlon, Sean ; Farrell, Steven ; Prabhat ; Cerati, Giuseppe ; Gray, Lindsey ; Klijnsma, Thomas ; Kowalkowski, Jim ; Spentzouris, Panagiotis ; Jean-Roch Vlimant ; Spiropulu, Maria ; Aurisano, Adam ; Hewes, V ; Tsaris, Aristeidis ; Terao, Kazuhiro ; Usher, Tracy</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24195623643</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Classifiers</topic><topic>Clustering</topic><topic>Data points</topic><topic>Graph neural networks</topic><topic>Graph theory</topic><topic>Graphical representations</topic><topic>Graphs</topic><topic>Machine learning</topic><topic>Message passing</topic><topic>Neural networks</topic><topic>Nodes</topic><topic>Particle tracking</topic><topic>Performance enhancement</topic><topic>Post-production processing</topic><topic>Sensors</topic><toplevel>online_resources</toplevel><creatorcontrib>Choma, Nicholas</creatorcontrib><creatorcontrib>Murnane, Daniel</creatorcontrib><creatorcontrib>Ju, Xiangyang</creatorcontrib><creatorcontrib>Calafiura, Paolo</creatorcontrib><creatorcontrib>Conlon, Sean</creatorcontrib><creatorcontrib>Farrell, Steven</creatorcontrib><creatorcontrib>Prabhat</creatorcontrib><creatorcontrib>Cerati, Giuseppe</creatorcontrib><creatorcontrib>Gray, Lindsey</creatorcontrib><creatorcontrib>Klijnsma, Thomas</creatorcontrib><creatorcontrib>Kowalkowski, Jim</creatorcontrib><creatorcontrib>Spentzouris, Panagiotis</creatorcontrib><creatorcontrib>Jean-Roch Vlimant</creatorcontrib><creatorcontrib>Spiropulu, Maria</creatorcontrib><creatorcontrib>Aurisano, Adam</creatorcontrib><creatorcontrib>Hewes, V</creatorcontrib><creatorcontrib>Tsaris, Aristeidis</creatorcontrib><creatorcontrib>Terao, Kazuhiro</creatorcontrib><creatorcontrib>Usher, Tracy</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Choma, Nicholas</au><au>Murnane, Daniel</au><au>Ju, Xiangyang</au><au>Calafiura, Paolo</au><au>Conlon, Sean</au><au>Farrell, Steven</au><au>Prabhat</au><au>Cerati, Giuseppe</au><au>Gray, Lindsey</au><au>Klijnsma, Thomas</au><au>Kowalkowski, Jim</au><au>Spentzouris, Panagiotis</au><au>Jean-Roch Vlimant</au><au>Spiropulu, Maria</au><au>Aurisano, Adam</au><au>Hewes, V</au><au>Tsaris, Aristeidis</au><au>Terao, Kazuhiro</au><au>Usher, Tracy</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Track Seeding and Labelling with Embedded-space Graph Neural Networks</atitle><jtitle>arXiv.org</jtitle><date>2020-06-30</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promising of these solutions, graph neural networks (GNN), process the event as a graph that connects track measurements (detector hits corresponding to nodes) with candidate line segments between the hits (corresponding to edges). Detector information can be associated with nodes and edges, enabling a GNN to propagate the embedded parameters around the graph and predict node-, edge- and graph-level observables. Previously, message-passing GNNs have shown success in predicting doublet likelihood, and we here report updates on the state-of-the-art architectures for this task. In addition, the Exa.TrkX project has investigated innovations in both graph construction, and embedded representations, in an effort to achieve fully learned end-to-end track finding. Hence, we present a suite of extensions to the original model, with encouraging results for hitgraph classification. In addition, we explore increased performance by constructing graphs from learned representations which contain non-linear metric structure, allowing for efficient clustering and neighborhood queries of data points. We demonstrate how this framework fits in with both traditional clustering pipelines, and GNN approaches. The embedded graphs feed into high-accuracy doublet and triplet classifiers, or can be used as an end-to-end track classifier by clustering in an embedded space. A set of post-processing methods improve performance with knowledge of the detector physics. Finally, we present numerical results on the TrackML particle tracking challenge dataset, where our framework shows favorable results in both seeding and track finding.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2020-06 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2419562364 |
source | Freely Accessible Journals |
subjects | Classifiers Clustering Data points Graph neural networks Graph theory Graphical representations Graphs Machine learning Message passing Neural networks Nodes Particle tracking Performance enhancement Post-production processing Sensors |
title | Track Seeding and Labelling with Embedded-space Graph Neural Networks |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T10%3A00%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Track%20Seeding%20and%20Labelling%20with%20Embedded-space%20Graph%20Neural%20Networks&rft.jtitle=arXiv.org&rft.au=Choma,%20Nicholas&rft.date=2020-06-30&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2419562364%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2419562364&rft_id=info:pmid/&rfr_iscdi=true |