{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T10:21:08Z","timestamp":1780482068137,"version":"3.54.1"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T00:00:00Z","timestamp":1636934400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T00:00:00Z","timestamp":1636934400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000001","name":"national science foundation","doi-asserted-by":"publisher","award":["Cooperative Agreement OAC-1836650"],"award-info":[{"award-number":["Cooperative Agreement OAC-1836650"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"national science foundation","doi-asserted-by":"publisher","award":["Cooperative Agreement OAC-1836650"],"award-info":[{"award-number":["Cooperative Agreement OAC-1836650"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"u.s. department of energy, office of science, office of high energy physics early career research program","award":["DE-SC0021187"],"award-info":[{"award-number":["DE-SC0021187"]}]},{"DOI":"10.13039\/100000015","name":"u.s. department of energy","doi-asserted-by":"crossref","award":["DE-SC0007968"],"award-info":[{"award-number":["DE-SC0007968"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Softw Big Sci"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well suited to address a variety of reconstruction problems in high-energy particle physics. In particular, particle tracking data are naturally represented as a graph by identifying silicon tracker hits as nodes and particle trajectories as edges, given a set of hypothesized edges, edge-classifying GNNs identify those corresponding to real particle trajectories. In this work, we adapt the physics-motivated interaction network (IN) GNN toward the problem of particle tracking in pileup conditions similar to those expected at the high-luminosity Large Hadron Collider. Assuming idealized hit filtering at various particle momenta thresholds, we demonstrate the IN\u2019s excellent edge-classification accuracy and tracking efficiency through a suite of measurements at each stage of GNN-based tracking: graph construction, edge classification, and track building. The proposed IN architecture is substantially smaller than previously studied GNN tracking architectures; this is particularly promising as a reduction in size is critical for enabling GNN-based tracking in constrained computing environments. Furthermore, the IN may be represented as either a set of explicit matrix operations or a message passing GNN. Efforts are underway to accelerate each representation via heterogeneous computing resources towards both high-level and low-latency triggering applications.<\/jats:p>","DOI":"10.1007\/s41781-021-00073-z","type":"journal-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T18:02:27Z","timestamp":1636999347000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Charged Particle Tracking via Edge-Classifying Interaction Networks"],"prefix":"10.1007","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5890-0445","authenticated-orcid":false,"given":"Gage","family":"DeZoort","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Savannah","family":"Thais","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Duarte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vesal","family":"Razavimaleki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Atkinson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isobel","family":"Ojalvo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Neubauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Elmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,11,15]]},"reference":[{"key":"73_CR1","doi-asserted-by":"publisher","first-page":"032033","DOI":"10.1088\/1742-6596\/119\/3\/032033","volume":"119","author":"G Piacquadio","year":"2008","unstructured":"Piacquadio G, Prokofiev K, Wildauer A (2008) Primary vertex reconstruction in the ATLAS experiment at LHC. J Phys Conf Ser 119:032033. https:\/\/doi.org\/10.1088\/1742-6596\/119\/3\/032033","journal-title":"J Phys Conf Ser"},{"key":"73_CR2","doi-asserted-by":"publisher","unstructured":"CMS Collaboration (2014) Description and performance of track and primary-vertex reconstruction with the CMS tracker. JINST 9(10):P10009. https:\/\/doi.org\/10.1088\/1748-0221\/9\/10\/P10009. arXiv:1405.6569","DOI":"10.1088\/1748-0221\/9\/10\/P10009"},{"key":"73_CR3","doi-asserted-by":"publisher","unstructured":"ATLAS Collaboration (2017) Jet reconstruction and performance using particle flow with the ATLAS detector. Eur Phys J C 77:466. https:\/\/doi.org\/10.1140\/epjc\/s10052-017-5031-2. arXiv:1703.10485","DOI":"10.1140\/epjc\/s10052-017-5031-2"},{"key":"73_CR4","doi-asserted-by":"publisher","first-page":"P10003","DOI":"10.1088\/1748-0221\/12\/10\/P10003","volume":"12","author":"CMS Collaboration","year":"2017","unstructured":"Collaboration CMS (2017) Particle-flow reconstruction and global event description with the CMS detector. JINST 12:P10003. https:\/\/doi.org\/10.1088\/1748-0221\/12\/10\/P10003. arXiv:1706.04965","journal-title":"JINST"},{"key":"73_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2019.11.001","volume":"841","author":"AJ Larkoski","year":"2020","unstructured":"Larkoski AJ, Moult I, Nachman B (2020) Jet substructure at the large hadron collider: a review of recent advances in theory and machine learning. Phys Rep 841:1. https:\/\/doi.org\/10.1016\/j.physrep.2019.11.001. arXiv:1709.04464","journal-title":"Phys Rep"},{"key":"73_CR6","doi-asserted-by":"publisher","unstructured":"CMS Collaboration (2018) Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV. JINST 13(05):P05011. https:\/\/doi.org\/10.1088\/1748-0221\/13\/05\/P05011. arXiv:1712.07158","DOI":"10.1088\/1748-0221\/13\/05\/P05011"},{"key":"73_CR7","doi-asserted-by":"publisher","unstructured":"ATLAS Collaboration (2018) Measurements of b-jet tagging efficiency with the ATLAS detector using $$t{\\overline{t}}$$ events at $$\\sqrt{s}=13$$ TeV. JHEP 08:089. https:\/\/doi.org\/10.1007\/JHEP08(2018)089. arXiv:1805.01845","DOI":"10.1007\/JHEP08(2018)089"},{"key":"73_CR8","doi-asserted-by":"publisher","unstructured":"ATLAS Collaboration (2017) Performance of the ATLAS track reconstruction algorithms in dense environments in LHC run 2. Eur Phys J C 77(10):673. https:\/\/doi.org\/10.1140\/epjc\/s10052-017-5225-7. arXiv:1704.07983","DOI":"10.1140\/epjc\/s10052-017-5225-7"},{"key":"73_CR9","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1016\/0010-4655(89)90249-X","volume":"57","author":"P Billoir","year":"1989","unstructured":"Billoir P (1989) Progressive track recognition with a Kalman-like fitting procedure. Comput Phys Commun 57:390. https:\/\/doi.org\/10.1016\/0010-4655(89)90249-X","journal-title":"Comput Phys Commun"},{"key":"73_CR10","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/0168-9002(90)91835-Y","volume":"294","author":"P Billoir","year":"1990","unstructured":"Billoir P, Qian S (1990) Simultaneous pattern recognition and track fitting by the Kalman filtering method. Nucl Instrum Methods A 294:219. https:\/\/doi.org\/10.1016\/0168-9002(90)91835-Y","journal-title":"Nucl Instrum Methods A"},{"key":"73_CR11","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/S0168-9002(97)00705-5","volume":"395","author":"R Mankel","year":"1997","unstructured":"Mankel R (1997) A concurrent track evolution algorithm for pattern recognition in the hera-b main tracking system. Nucl Instrum Methods A 395:169. https:\/\/doi.org\/10.1016\/S0168-9002(97)00705-5","journal-title":"Nucl Instrum Methods A"},{"key":"73_CR12","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1016\/0168-9002(87)90887-4","volume":"262","author":"R Fr\u00fchwirth","year":"1987","unstructured":"Fr\u00fchwirth R (1987) Application of Kalman filtering to track and vertex fitting. Nucl Instrum Methods A 262:444. https:\/\/doi.org\/10.1016\/0168-9002(87)90887-4","journal-title":"Nucl Instrum Methods A"},{"key":"73_CR13","unstructured":"CMS Collaboration (2018) Expected performance of the physics objects with the upgraded CMS detector at the HL-LHC, CMS Note CMS-NOTE-2018-006. CERN-CMS-NOTE-2018-006"},{"key":"73_CR14","doi-asserted-by":"publisher","unstructured":"Apollinari G et\u00a0al (eds) (2017) High-luminosity large hadron collider (HL-LHC): technical design report V. 0.1, vol 4\/2017. CERN. https:\/\/doi.org\/10.23731\/CYRM-2017-004","DOI":"10.23731\/CYRM-2017-004"},{"key":"73_CR15","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","volume":"34","author":"MM Bronstein","year":"2017","unstructured":"Bronstein MM et al (2017) Geometric deep learning: going beyond Euclidean data. IEEE Signal Process Mag 34:18. https:\/\/doi.org\/10.1109\/MSP.2017.2693418. arXiv:1611.08097","journal-title":"IEEE Signal Process Mag"},{"key":"73_CR16","doi-asserted-by":"publisher","unstructured":"Zhang Z, Cui P, Zhu W (2020) Deep learning on graphs. A survey. IEEE Trans Knowl Data Eng (1):1. https:\/\/doi.org\/10.1109\/TKDE.2020.2981333. arXiv:1812.04202","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"73_CR17","doi-asserted-by":"publisher","unstructured":"Zhou J et al (2020) Graph neural networks: a review of methods and applications.AI Open 1:57-81. https:\/\/doi.org\/10.1016\/j.aiopen.2021.01.001. arXiv:1812. 08434","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"73_CR18","doi-asserted-by":"publisher","unstructured":"Wu Z et al (2020) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2020.2978386. arXiv:1901.00596","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"73_CR19","doi-asserted-by":"publisher","unstructured":"Scarselli F et\u00a0al (2009) The graph neural network model. IEEE Trans Neural Netw 20(1):61. https:\/\/doi.org\/10.1109\/TNN.2008.2005605","DOI":"10.1109\/TNN.2008.2005605"},{"key":"73_CR20","doi-asserted-by":"publisher","unstructured":"Qi CR, Su H, Mo K, Guibas LJ (2017) PointNet: deep learning on point sets for 3D classification and segmentation. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). https:\/\/arxiv.org\/abs\/1612.00593. https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"key":"73_CR21","unstructured":"Gilmer J et\u00a0al (2017) Neural message passing for quantum chemistry. In: Proceedings of the 34th international conference on machine learning, volume\u00a070 of Proceedings of machine learning research, p\u00a01263. https:\/\/arxiv.org\/abs\/1704.01212"},{"key":"73_CR22","unstructured":"Battaglia PW et\u00a0al (2016) Interaction networks for learning about objects, relations and physics. In: Lee D et\u00a0al (eds) Advances in neural information processing systems, vol 29, p\u00a04502. Curran Associates, Inc. https:\/\/arxiv.org\/abs\/1612.00222"},{"key":"73_CR23","unstructured":"Battaglia PW et al (2018) Relational inductive biases, deep learning. and graph networks. https:\/\/arxiv.org\/abs\/1806.01261"},{"key":"73_CR24","doi-asserted-by":"publisher","unstructured":"Wang Y et\u00a0al (2019) Dynamic graph CNN for learning on point clouds. ACM Trans Graph. https:\/\/doi.org\/10.1145\/3326362. https:\/\/arxiv.org\/abs\/1801.07829","DOI":"10.1145\/3326362"},{"key":"73_CR25","doi-asserted-by":"publisher","unstructured":"Duarte J, Vlimant J-R (2020) Graph neural networks for particle tracking and reconstruction. In: Calafiura P, Rousseau D, Terao K (eds) Artificial intelligence for high energy physics. World Scientific Publishing, p 12. https:\/\/arxiv.org\/abs\/2012.01249. https:\/\/doi.org\/10.1142\/12200(Submitted to Int. J. Mod. Phys. A)","DOI":"10.1142\/12200"},{"key":"73_CR26","doi-asserted-by":"publisher","unstructured":"Shlomi J, Battaglia P, Vlimant J-R (2020) Graph neural networks in particle physics. Mach Learn Sci Technol 2:021001. https:\/\/doi.org\/10.1088\/2632-2153\/abbf9a. arXiv:2007.13681","DOI":"10.1088\/2632-2153\/abbf9a"},{"key":"73_CR27","unstructured":"Farrell S et\u00a0al (2018) Novel deep learning methods for track reconstruction. In: 4th international workshop connecting the dots 2018. https:\/\/arxiv.org\/abs\/1810.06111"},{"key":"73_CR28","unstructured":"Ju X et\u00a0al (2019) Graph neural networks for particle reconstruction in high energy physics detectors. In: Machine learning and the physical sciences workshop at the 33rd annual conference on neural information processing systems. https:\/\/arxiv.org\/abs\/2003.11603"},{"key":"73_CR29","unstructured":"Heintz A et\u00a0al (2020) Accelerated charged particle tracking with graph neural networks on FPGAs. In: 3rd machine learning and the physical sciences workshop at the 34th annual conference on neural information processing systems, vol 12. https:\/\/arxiv.org\/abs\/2012.01563"},{"key":"73_CR30","unstructured":"Ju X et\u00a0al (2021) Performance of a geometric deep learning pipeline for HL-LHC particle tracking, vol 3. https:\/\/arxiv.org\/abs\/2103.06995(Submitted to Eur. Phys. J. C)"},{"key":"73_CR31","doi-asserted-by":"publisher","first-page":"012010","DOI":"10.1103\/PhysRevD.102.012010","volume":"102","author":"EA Moreno","year":"2020","unstructured":"Moreno EA et al (2020) Interaction networks for the identification of boosted $$H \\rightarrow b{\\overline{b}}$$ decays. Phys Rev D 102:012010. https:\/\/doi.org\/10.1103\/PhysRevD.102.012010. https:\/\/arxiv.org\/abs\/1909.12285","journal-title":"Phys Rev D"},{"key":"73_CR32","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1140\/epjc\/s10052-020-7608-4","volume":"80","author":"EA Moreno","year":"2020","unstructured":"Moreno EA et al (2020) JEDI-net: a jet identification algorithm based on interaction networks. Eur Phys J C 80:58. https:\/\/doi.org\/10.1140\/epjc\/s10052-020-7608-4. https:\/\/arxiv.org\/abs\/1908.05318","journal-title":"Eur Phys J C"},{"key":"73_CR33","unstructured":"Besta M et al (2019) Graph processing on FPGAs: taxonomy, survey, challenges. arXiv:1903.06697"},{"key":"73_CR34","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1103\/RevModPhys.82.1419","volume":"82","author":"A Strandlie","year":"2010","unstructured":"Strandlie A, Fr\u00fchwirth R (2010) Track and vertex reconstruction: from classical to adaptive methods. Rev Mod Phys 82:1419. https:\/\/doi.org\/10.1103\/RevModPhys.82.1419","journal-title":"Rev Mod Phys"},{"key":"73_CR35","doi-asserted-by":"publisher","unstructured":"Amrouche S et\u00a0al (2020) The tracking machine learning challenge: accuracy phase. In: The NeurIPS \u201918 competition, p\u00a0231. https:\/\/arxiv.org\/abs\/1904.06778. https:\/\/doi.org\/10.1007\/978-3-030-29135-8_9","DOI":"10.1007\/978-3-030-29135-8_9"},{"key":"73_CR36","unstructured":"Fey M, Lenssen JE (2019) Fast graph representation learning with PyTorch Geometric. In: Representation learning on graphs and manifolds workshop at the 7th international conference on learning representations. arXiv:1903.02428"},{"key":"73_CR37","unstructured":"Paszke A et al (2019) PyTorch: an imperative style, high-performance deep learning library. In: Wallach H et al (eds) Advances in neural information processing systems, vol 32. Curran Associates, Inc. arXiv:1912. 01703"},{"key":"73_CR38","unstructured":"Ester M, Kriegel H-P, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the second international conference on knowledge discovery and data mining, p\u00a0226. AAAI Press"},{"key":"73_CR39","doi-asserted-by":"crossref","unstructured":"Biscarat C et\u00a0al (2021) Towards a realistic track reconstruction algorithm based on graph neural networks for the HL-LHC. In: 25th international conference on computing in high-energy and nuclear physics, vol 3. arXiv:2103. 00916","DOI":"10.1051\/epjconf\/202125103047"},{"key":"73_CR40","unstructured":"DeZoort G, Duarte J (2021) GageDeZoort\/interaction_network_paper: interaction networks for GNN-based particle tracking. https:\/\/doi.org\/10.5281\/zenodo.5558032. https:\/\/github.com\/GageDeZoort\/interaction_network_paper. Accessed 08 Oct 2021"},{"key":"73_CR41","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: 27th international conference on international conference on machine learning, ICML\u201910, p 807. Omnipress, Madison"},{"key":"73_CR42","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Gordon G, Dunson D, Dud\u00edk M (eds) 14th international conference on artificial intelligence and statistics, vol 15, p 315. JMLR, Fort Lauderdale, FL, USA, 4"},{"key":"73_CR43","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Bengio Y, LeCun Y (eds) 3rd international conference on learning representations. https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"73_CR44","doi-asserted-by":"crossref","unstructured":"Patwary MMA, Blair J, Manne F (2010) Experiments on union-find algorithms for the disjoint-set data structure. In: Festa P (ed) Experimental algorithms. Springer, Berlin, pp 411\u2013423","DOI":"10.1007\/978-3-642-13193-6_35"},{"key":"73_CR45","unstructured":"The PyTorch Team, TorchScript (2021). https:\/\/pytorch.org\/docs\/stable\/jit.html. Accessed 08 Oct 2021"},{"key":"73_CR46","doi-asserted-by":"publisher","unstructured":"Krupa J et\u00a0al (2021) Gpu coprocessors as a service for deep learning inference in high energy physics. Mach Learn Sci Technol 2(3):035005. https:\/\/doi.org\/10.1088\/2632-2153\/abec21. https:\/\/arxiv.org\/abs\/2007.10359","DOI":"10.1088\/2632-2153\/abec21"},{"key":"73_CR47","doi-asserted-by":"publisher","unstructured":"Rankin DS et\u00a0al (2020) FPGAs-as-a-service toolkit (FaaST). In: 2020 IEEE\/ACM international workshop on heterogeneous high-performance reconfigurable computing (H2RC). https:\/\/arxiv.org\/abs\/2010.08556. https:\/\/doi.org\/10.1109\/H2RC51942.2020.00010","DOI":"10.1109\/H2RC51942.2020.00010"},{"key":"73_CR48","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3389\/fdata.2020.604083","volume":"3","author":"M Wang","year":"2021","unstructured":"Wang M et al (2021) GPU-accelerated machine learning inference as a service for computing in neutrino experiments. Front Big Data 3:48. https:\/\/doi.org\/10.3389\/fdata.2020.604083. https:\/\/arxiv.org\/abs\/2009.04509","journal-title":"Front Big Data"},{"key":"73_CR49","doi-asserted-by":"publisher","unstructured":"Umuroglu Y et\u00a0al (2017) FINN: a framework for fast, scalable binarized neural network inference. In: Proceedings of the 2017 ACM\/SIGDA international symposium on field-programmable gate arrays, p 65. ACM, New York, NY, USA. https:\/\/arxiv.org\/abs\/1612.07119. https:\/\/doi.org\/10.1145\/3020078.3021744","DOI":"10.1145\/3020078.3021744"},{"key":"73_CR50","doi-asserted-by":"publisher","unstructured":"Blott M et\u00a0al (2018) FINN-R: An end-to-end deep-learning framework for fast exploration of quantized neural networks. ACM Trans Reconfig Technol Syst 11(12). https:\/\/doi.org\/10.1145\/3242897. https:\/\/arxiv.org\/abs\/1809.04570","DOI":"10.1145\/3242897"},{"key":"73_CR51","doi-asserted-by":"publisher","first-page":"7823","DOI":"10.1109\/ACCESS.2018.2890150","volume":"7","author":"A Shawahna","year":"2019","unstructured":"Shawahna A, Sait SM, El-Maleh A (2019) FPGA-based accelerators of deep learning networks for learning and classification: a review. IEEE Access 7:7823. https:\/\/doi.org\/10.1109\/ACCESS.2018.2890150. https:\/\/arxiv.org\/abs\/1901.00121","journal-title":"IEEE Access"},{"key":"73_CR52","doi-asserted-by":"publisher","unstructured":"Wang T, Wang C, Zhou X, Chen H (2019) An overview of FPGA based deep learning accelerators: challenges and opportunities. In: 2019 IEEE 21st international conference on high performance computing and communications; IEEE 17th international conference on smart city; IEEE 5th international conference on data science and systems (HPCC\/SmartCity\/DSS), p\u00a01674. https:\/\/arxiv.org\/abs\/1901.04988. https:\/\/doi.org\/10.1109\/HPCC\/SmartCity\/DSS.2019.00229","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00229"},{"key":"73_CR53","doi-asserted-by":"publisher","first-page":"P07027","DOI":"10.1088\/1748-0221\/13\/07\/P07027","volume":"13","author":"J Duarte","year":"2018","unstructured":"Duarte J et al (2018) Fast inference of deep neural networks in FPGAs for particle physics. JINST 13:P07027. https:\/\/doi.org\/10.1088\/1748-0221\/13\/07\/P07027. https:\/\/arxiv.org\/abs\/1804.06913","journal-title":"JINST"},{"key":"73_CR54","doi-asserted-by":"publisher","first-page":"P05026","DOI":"10.1088\/1748-0221\/15\/05\/p05026","volume":"15","author":"S Summers","year":"2020","unstructured":"Summers S et al (2020) Fast inference of boosted decision trees in FPGAs for particle physics. JINST 15:P05026. https:\/\/doi.org\/10.1088\/1748-0221\/15\/05\/p05026. https:\/\/arxiv.org\/abs\/2002.02534","journal-title":"JINST"},{"key":"73_CR55","doi-asserted-by":"publisher","unstructured":"Ngadiuba J et\u00a0al (2020) Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml. Mach Learn Sci Technol 2(1):015001. https:\/\/doi.org\/10.1088\/2632-2153\/aba042. https:\/\/arxiv.org\/abs\/2003.06308","DOI":"10.1088\/2632-2153\/aba042"},{"key":"73_CR56","doi-asserted-by":"publisher","unstructured":"Coelho CN et\u00a0al (2021) Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors. Nat Mach Intell. https:\/\/doi.org\/10.1038\/s42256-021-00356-5. https:\/\/arxiv.org\/abs\/2006.10159","DOI":"10.1038\/s42256-021-00356-5"},{"key":"73_CR57","doi-asserted-by":"publisher","unstructured":"\u00c5arrestad T et\u00a0al (2021) Fast convolutional neural networks on FPGAs with hls4ml. Mach Learn Sci Technol 2(4):045015. https:\/\/doi.org\/10.1088\/2632-2153\/ac0ea1. https:\/\/arxiv.org\/abs\/2101.05108","DOI":"10.1088\/2632-2153\/ac0ea1"},{"key":"73_CR58","doi-asserted-by":"publisher","first-page":"44","DOI":"10.3389\/fdata.2020.598927","volume":"3","author":"Y Iiyama","year":"2021","unstructured":"Iiyama Y et al (2021) Distance-weighted graph neural networks on FPGAs for real-time particle reconstruction in high energy physics. Front Big Data 3:44. https:\/\/doi.org\/10.3389\/fdata.2020.598927. https:\/\/arxiv.org\/abs\/2008.03601","journal-title":"Front Big Data"},{"key":"73_CR59","doi-asserted-by":"publisher","unstructured":"Moons B, Goetschalckx K, Berckelaer NV, Verhelst M (2017) Minimum energy quantized neural networks. In: 2017 51st asilomar conference on signals, systems, and computers, p\u00a01921. https:\/\/arxiv.org\/abs\/1711.00215. https:\/\/doi.org\/10.1109\/ACSSC.2017.8335699","DOI":"10.1109\/ACSSC.2017.8335699"},{"key":"73_CR60","unstructured":"Courbariaux M, Bengio Y, David J-P (2015) BinaryConnect: training deep neural networks with binary weights during propagations. In: Cortes C et\u00a0al (eds) Advances in Neural Information Processing Systems, vol 28, p\u00a03123. Curran Associates, Inc. https:\/\/arxiv.org\/abs\/1511.00363"},{"key":"73_CR61","doi-asserted-by":"crossref","unstructured":"Zhang D, Yang J, Ye D, Hua G (2018) LQ-nets: learned quantization for highly accurate and compact deep neural networks. In: Proceedings of the European conference on computer vision (ECCV), p\u00a0365. https:\/\/arxiv.org\/abs\/1807.10029","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"73_CR62","unstructured":"Li F, Liu B (2016) Ternary weight networks. https:\/\/arxiv.org\/abs\/1605.04711"},{"key":"73_CR63","unstructured":"Zhou S et\u00a0al (2016) DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. https:\/\/arxiv.org\/abs\/1606.06160"},{"key":"73_CR64","unstructured":"Hubara I et\u00a0al (2018) Quantized neural networks: training neural networks with low precision weights and activations. J Mach Learn Res 18(187):1. https:\/\/arxiv.org\/abs\/1609.07061"},{"key":"73_CR65","doi-asserted-by":"publisher","unstructured":"Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) XNOR-Net: ImageNet classification using binary convolutional neural networks. In: 14th European conference on computer vision (ECCV). Springer International Publishing, Cham, p 525. https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32. https:\/\/arxiv.org\/abs\/1603.05279","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"73_CR66","unstructured":"Micikevicius P et\u00a0al (2018) Mixed precision training. In: 6th international conference on learning representations. https:\/\/arxiv.org\/abs\/1710.03740"},{"key":"73_CR67","doi-asserted-by":"publisher","unstructured":"Zhuang B et\u00a0al (2018) Towards effective low-bitwidth convolutional neural networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, p\u00a07920. https:\/\/arxiv.org\/abs\/1711.00205. https:\/\/doi.org\/10.1109\/CVPR.2018.00826","DOI":"10.1109\/CVPR.2018.00826"},{"key":"73_CR68","unstructured":"Wang N et\u00a0al (2018) Training deep neural networks with 8-bit floating point numbers. In: Bengio S et\u00a0al (eds) Advances in neural information processing systems, vol 31, p\u00a07675. Curran Associates, Inc. https:\/\/arxiv.org\/abs\/1812.08011"},{"key":"73_CR69","unstructured":"Coelho C (2019) QKeras. https:\/\/github.com\/google\/qkeras. Accessed 08 Oct 2021"},{"key":"73_CR70","doi-asserted-by":"publisher","unstructured":"Pappalardo A (2020) Xilinx\/brevitas. https:\/\/doi.org\/10.5281\/zenodo.3333552","DOI":"10.5281\/zenodo.3333552"},{"key":"73_CR71","unstructured":"LeCun Y, Denker JS, Solla SA (1990) In: Touretzky DS (ed) Optimal brain damage. In: Advances in neural information processing systems, vol 2. Morgan-Kaufmann, p 598"},{"key":"73_CR72","unstructured":"Han S, Mao H, Dally WJ (2016) Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: 4th international conference on learning representations. https:\/\/arxiv.org\/abs\/1510.00149"},{"key":"73_CR73","unstructured":"Frankle J, Carbin M (2019) The lottery ticket hypothesis: training pruned neural networks. In: 7th international conference on learning representations. https:\/\/arxiv.org\/abs\/1803.03635"},{"key":"73_CR74","unstructured":"Zhou H, Lan J, Liu R, Yosinski J (2019) Deconstructing lottery tickets: zeros, signs, and the supermask. In: Wallach H et\u00a0al (eds) Advances in neural information processing systems, vol 32, p\u00a03597. Curran Associates, Inc. https:\/\/arxiv.org\/abs\/1905.01067"},{"key":"73_CR75","unstructured":"Blalock D, Ortiz JJG, Frankle J, Guttag J (2020) What is the state of neural network pruning? In: 4th conference on machine learning and systems. https:\/\/arxiv.org\/abs\/2003.03033"},{"key":"73_CR76","doi-asserted-by":"publisher","first-page":"94","DOI":"10.3389\/frai.2021.676564","volume":"4","author":"B Hawks","year":"2021","unstructured":"Hawks B et al (2021) Ps and Qs: quantization-aware pruning for efficient low latency neural network inference. Front AI 4:94. https:\/\/doi.org\/10.3389\/frai.2021.676564. https:\/\/arxiv.org\/abs\/2102.11289","journal-title":"Front AI"},{"key":"73_CR77","doi-asserted-by":"publisher","unstructured":"Loncar V et al (2021) fastmachinelearning\/hls4ml. https:\/\/doi.org\/10.5281\/zenodo.4447439","DOI":"10.5281\/zenodo.4447439"},{"key":"73_CR78","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1140\/epjc\/s10052-019-7113-9","volume":"79","author":"SR Qasim","year":"2019","unstructured":"Qasim SR, Kieseler J, Iiyama Y, Pierini M (2019) Learning representations of irregular particle-detector geometry with distance-weighted graph networks. Eur Phys J C 79:608. https:\/\/doi.org\/10.1140\/epjc\/s10052-019-7113-9. https:\/\/arxiv.org\/abs\/1902.07987","journal-title":"Eur Phys J C"},{"key":"73_CR79","unstructured":"Vaswani A et\u00a0al (2017) Attention is all you need. In: Guyon I et\u00a0al (eds) Advances in neural information processing systems, vol\u00a030, p\u00a05998. Curran Associates, Inc. https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"73_CR80","unstructured":"Kitaev N, Kaiser \u0141, Levskaya A (2020) Reformer: the efficient transformer. In: 8th international conference on learning representations. https:\/\/arxiv.org\/abs\/2001.04451"},{"key":"73_CR81","unstructured":"Choromanski K et al (2021) Rethinking attention with performers. In: 9th international conference on learning representations. arXiv:2009. 14794"}],"container-title":["Computing and Software for Big Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-021-00073-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41781-021-00073-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-021-00073-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,26]],"date-time":"2021-12-26T11:08:07Z","timestamp":1640516887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41781-021-00073-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,15]]},"references-count":81,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["73"],"URL":"https:\/\/doi.org\/10.1007\/s41781-021-00073-z","relation":{},"ISSN":["2510-2036","2510-2044"],"issn-type":[{"value":"2510-2036","type":"print"},{"value":"2510-2044","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,15]]},"assertion":[{"value":"12 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"26"}}