Abstract.
At the Large Hadron Collider, the high-transverse-momentum events studied by experimental collaborations occur in coincidence with parasitic low-transverse-momentum collisions, usually referred to as pileup. Pileup mitigation is a key ingredient of the online and offline event reconstruction as pileup affects the reconstruction accuracy of many physics observables. We present a classifier based on Graph Neural Networks, trained to retain particles coming from high-transverse-momentum collisions, while rejecting those coming from pileup collisions. This model is designed as a refinement of the PUPPI algorithm (D. Bertolini et al., JHEP 10, 059 (2014)), employed in many LHC data analyses since 2015. Thanks to an extended basis of input information and the learning capabilities of the considered network architecture, we show an improvement in pileup-rejection performances with respect to state-of-the-art solutions.
Similar content being viewed by others
References
ATLAS Collaboration (G. Aad et al.), JINST 3, S08003 (2008)
CMS Collaboration (S. Chatrchyan et al.), JINST 3, S08004 (2008)
CMS Collaboration (S. Chatrchyan et al.), JINST 9, P10009 (2014) arXiv:1405.6569
ATLAS Collaboration, ATLAS-CONF-2010-069 (2010)
M. Cacciari, J. Rojo, G.P. Salam, G. Soyez, JHEP 12, 032 (2008) arXiv:0810.1304
D. Krohn, M.D. Schwartz, M. Low, L.T. Wang, Phys. Rev. D 90, 065020 (2014) arXiv:1309.4777
M. Cacciari, G.P. Salam, G. Soyez, Phys. Rev. D 92, 014003 (2015) arXiv:1404.7353
P. Berta, M. Spousta, D.W. Miller, R. Leitner, JHEP 06, 092 (2014) arXiv:1403.3108
G. Soyez, G.P. Salam, J. Kim, S. Dutta, M. Cacciari, Phys. Rev. Lett. 110, 162001 (2013) arXiv:1211.2811
M. Cacciari, G.P. Salam, G. Soyez, Eur. Phys. J. C 75, 59 (2015) arXiv:1407.0408
D. Bertolini, P. Harris, M. Low, N. Tran, JHEP 10, 059 (2014) arXiv:1407.6013
Tech. Rep. CMS-PAS-JME-14-001, CERN, Geneva https://cds.cern.ch/record/1751454 (2014)
Tech. Rep. ATLAS-CONF-2017-065, CERN, Geneva, https://cds.cern.ch/record/2281055 (2017)
Y. Li, D. Tarlow, M. Brockschmidt, R.S. Zemel, CoRR abs/1511.05493 (2015) arXiv:1511.05493
J. Orbach, Arch. Gen. Psych. 7, 218 (1962)
K. Cho, B. van Merrienboer, D. Bahdanau, Y. Bengio, CoRR abs/1409.1259 (2014) arXiv:1409.1259
A. Radovic et al., Nature 560, 41 (2018)
CMS Collaboration, Tech. Rep. CMS-DP-2017-027, CERN, Geneva, http://cds.cern.ch/record/2275226 (2017)
ATLAS Collaboration, Tech. Rep. ATL-PHYS-PUB-2017-003, CERN, Geneva, http://cds.cern.ch/record/2255226 (2017)
A. Aurisano et al., JINST 11, P09001 (2016) arXiv:1604.01444
I. Henrion, Neural message passing for jet physics, https://cims.nyu.edu/~bruna/Media/nmp_jet.pdf (2017)
M. Abdughani, J. Ren, L. Wu, J.M. Yang (2018) arXiv:1807.09088
N. Choma, CoRR abs/1809.06166 (2018)
P.T. Komiske, E.M. Metodiev, B. Nachman, M.D. Schwartz, JHEP 12, 051 (2017) arXiv:1707.08600
CMS Collaboration (S. Chatrchyan et al.), JINST 9, P10009 (2014) arXiv:1405.6569
ATLAS Collaboration (M. Aaboud et al.), Eur. Phys. J. C 77, 466 (2017) arXiv:1703.10485
CMS Collaboration (A.M. Sirunyan et al.), JINST 12, P10003 (2017) arXiv:1706.04965
T. Sjöstrand et al., Comput. Phys. Commun. 191, 159 (2015) arXiv:1410.3012
R. Corke, T. Sjöstrand, JHEP 03, 032 (2011) arXiv:1011.1759
DELPHES 3 Collaboration (J. de Favereau et al.), JHEP 02, 057 (2014) arXiv:1307.6346
R. Brun, F. Rademakers, Nucl. Instrum. Methods A 389, 81 (1997)
D.P. Kingma, J. Ba, CoRR abs/1412.6980 (2014) arXiv:1412.6980
J. Gilmer, S.S. Schoenholz, P.F. Riley, O. Vinyals, G.E. Dahl, CoRR abs/1704.01212 (2017) arXiv:1704.01212
K. He, X. Zhang, S. Ren, J. Sun, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
F. Chollet, Keras https://keras.io (2015)
M. Abadi, TensorFlow: Large-scale machine learning on heterogeneous systems (2015) software available from https://www.tensorflow.org/
Microsoft, Gated graph neural network samples, https://github.com/Microsoft/gated-graph-neural-network-samples (2017)
M. Cacciari, G.P. Salam, G. Soyez, JHEP 04, 063 (2008) arXiv:0802.1189
M. Cacciari, G.P. Salam, G. Soyez, Eur. Phys. J. C 72, 1896 (2012) arXiv:1111.6097
M. Cacciari, G.P. Salam, Phys. Lett. B 641, 57 (2006) hep-ph/0512210
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
The EPJ Publishers remain neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Arjona Martínez, J., Cerri, O., Spiropulu, M. et al. Pileup mitigation at the Large Hadron Collider with graph neural networks. Eur. Phys. J. Plus 134, 333 (2019). https://doi.org/10.1140/epjp/i2019-12710-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1140/epjp/i2019-12710-3