Fetching the paper…

Reading the bibliography…

2022

Leveraging universality of jet taggers through transfer learning

Dreyer, Frédéric A., Grabarczyk, Radosław, Monni, Pier Francesco

Original
PDF
Post on X

Understand

A significant challenge in the tagging of boosted objects via machine-learning technology is the prohibitive computational cost associated with training sophisticated models.

Nevertheless, the universality of QCD suggests that a large amount of the information learnt in the training is common to different physical signals and experimental setups.
In this article, we explore the use of transfer learning techniques to develop fast and data-efficient jet taggers that leverage such universality.
We consider the graph neural networks LundNet and ParticleNet, and introduce two prescriptions to transfer an existing tagger into a new signal based either on fine-tuning all the weights of a model or alternatively on freezing a fraction of them.

Leveraging universality of jet taggers through transfer learning · Around

Built on

J. H. Collins, K. Howe, and B. Nachman, Extending the search for new resonances with machine learning
Original
1902
Earlier work this paper cites.
K. Datta, A. Larkoski, and B. Nachman, Automating the Construction of Jet Observables with Machine Learning
Original
1902
Earlier work this paper cites.
H. Qu and L. Gouskos, ParticleNet: Jet Tagging via Particle Clouds
Original
1902
Earlier work this paper cites.
A. Chakraborty, S. H. Lim, and M. M. Nojiri, Interpretable deep learning for two-prong jet classification with jet spectra
Original
1904
Earlier work this paper cites.
G. Bewick, S. Ferrario Ravasio, P. Richardson, and M. H. Seymour, Logarithmic accuracy of angular-ordered parton showers
Original
1904
Earlier work this paper cites.
W. Hu, B. Liu, J. Gomes, M. Zitnik, P. Liang, V. S. Pande, and J. Leskovec, Pre-training Graph Neural Networks
Original
1905
Earlier work this paper cites.
E. A. Moreno, O. Cerri, J. M. Duarte, H. B. Newman, T. Q. Nguyen, A. Periwal, M. Pierini, A. Serikova, M. Spiropulu, and J.-R. Vlimant, JEDI-net: a jet identification algorithm based on interaction networks
Original
1908
Earlier work this paper cites.
P. F. Monni, P. Nason, E. Re, M. Wiesemann, and G. Zanderighi, MiNNLO PS
Original
1908
Earlier work this paper cites.
E. A. Moreno, T. Q. Nguyen, J.-R. Vlimant, O. Cerri, H. B. Newman, A. Periwal, M. Spiropulu, J. M. Duarte, and M. Pierini, Interaction networks for the identification of boosted H → b b ¯ H\rightarrow b\overline{b} decays
Original
1909
Earlier work this paper cites.
arXiv:1909.01315 [cs.LG]
Original
M. Wang, D. Zheng, Z. Ye, Q. Gan, M. Li, X. Song, J. Zhou, C. Ma, L. Yu, Y. Gai, T. Xiao, T. He, G. Karypis, J. Li, and Z. Zhang, Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks · 1909
Earlier work this paper cites.
F. Zhuang, Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, and Q. He, A Comprehensive Survey on Transfer Learning
Original
1911
Earlier work this paper cites.
B. Andersson, G. Gustafson, L. Lonnblad, and U. Pettersson, Coherence Effects in Deep Inelastic Scattering
1989
Earlier work this paper cites.
Y. L. Dokshitzer, G. Leder, S. Moretti, and B. Webber, Better jet clustering algorithms
1997
Earlier work this paper cites.
A. Andreassen, B. Nachman, and D. Shih, Simulation Assisted Likelihood-free Anomaly Detection
Original
2001
Earlier work this paper cites.
M. Dasgupta, F. A. Dreyer, K. Hamilton, P. F. Monni, G. P. Salam, and G. Soyez, Parton showers beyond leading logarithmic accuracy
Original
2002
Earlier work this paper cites.
J. R. Forshaw, J. Holguin, and S. Plätzer, Building a consistent parton shower
Original
2003
Earlier work this paper cites.
P. F. Monni, E. Re, and M. Wiesemann, MiNNLO PS {}_{\text{PS}} : optimizing 2 → 1 2\rightarrow 1 hadronic processes
Original
2006
Earlier work this paper cites.
G. Kasieczka, S. Marzani, G. Soyez, and G. Stagnitto, Towards Machine Learning Analytics for Jet Substructure
Original
2007
Earlier work this paper cites.
A. Lifson, G. P. Salam, and G. Soyez, Calculating the primary Lund Jet Plane density
Original
2007
Earlier work this paper cites.
M. Cacciari, G. P. Salam, and G. Soyez, The anti- k t k_{t} jet clustering algorithm
2008
Earlier work this paper cites.
H. D. III, Frustratingly Easy Domain Adaptation
Original
2009
Earlier work this paper cites.
S. J. Pan and Q. Yang, A Survey on Transfer Learning
2010
Earlier work this paper cites.
Z. Nagy and D. E. Soper, Summations of large logarithms by parton showers
Original
2011
Earlier work this paper cites.
PMLR, Fort Lauderdale, FL, USA, 11–13 Apr, 2011
X. Glorot, A. Bordes, and Y. Bengio, “Deep sparse rectifier neural networks,” in Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics · 2011
Earlier work this paper cites.
arXiv:2012.08526 [hep-ph]
Original
F. A. Dreyer and H. Qu, Jet tagging in the Lund plane with graph networks · 2012
Earlier work this paper cites.

Similar

Association for Computational Linguistics, Jeju Island, Korea, July, 2012
F. Li, S. J. Pan, O. Jin, Q. Yang, and X. Zhu, “Cross-domain co-extraction of sentiment and topic lexicons,” in Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2012
Cited alongside, same era.
K. Hamilton, P. Nason, E. Re, and G. Zanderighi, NNLOPS simulation of Higgs boson production
Original
2013
Cited alongside, same era.
R. B. Girshick, J. Donahue, T. Darrell, and J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation
Original
2013
Cited alongside, same era.
S. Alioli, C. W. Bauer, C. Berggren, F. J. Tackmann, J. R. Walsh, and S. Zuberi, Matching Fully Differential NNLO Calculations and Parton Showers
Original
2014
Cited alongside, same era.
D. P. Kingma and J. Ba, Adam: A Method for Stochastic Optimization

Then

S. H. Lim and M. M. Nojiri, Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case
Original
2018
Later among the works it cites.
A. Butter, G. Kasieczka, T. Plehn, and M. Russell, Deep-learned Top Tagging with a Lorentz Layer
Original
2018
Later among the works it cites.
T. Cheng, Recursive Neural Networks in Quark/Gluon Tagging
Original
2018
Later among the works it cites.
S. Macaluso and D. Shih, Pulling Out All the Tops with Computer Vision and Deep Learning
Original
2018
Later among the works it cites.
D. Guest, K. Cranmer, and D. Whiteson, Deep Learning and Its Application to LHC Physics
2018

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

2014

Cited alongside, same era.

J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, How transferable are features in deep neural networks?

2014

Cited alongside, same era.

JMLR.org, 2014

J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell, “Decaf: A deep convolutional activation feature for generic visual recognition,” in Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32 · 2014

Cited alongside, same era.

L. G. Almeida, M. Backović, M. Cliche, S. J. Lee, and M. Perelstein, Playing Tag with ANN: Boosted Top Identification with Pattern Recognition

2015

Cited alongside, same era.

S. Höche, Y. Li, and S. Prestel, Drell-Yan lepton pair production at NNLO QCD with parton showers

2015

Cited alongside, same era.

PMLR, Lille, France, 07–09 Jul, 2015

S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Proceedings of the 32nd International Conference on Machine Learning · 2015

Cited alongside, same era.

Association for Computing Machinery, New York, NY, USA, 2015

H.-W. Ng, V. D. Nguyen, V. Vonikakis, and S. Winkler, “Deep learning for emotion recognition on small datasets using transfer learning,” in Proceedings of the 2015 ACM on International Conference on Multimodal Interaction · 2015

Cited alongside, same era.

T. Sjöstrand, S. Ask, J. Christiansen, R. Corke, N. Desai, P. Ilten, S. Mrenna, S. Prestel, C. Rasmussen, and P. Skands, An introduction to PYTHIA 8.2

2015

Cited alongside, same era.

Later among the works it cites.

P. T. Komiske, E. M. Metodiev, and J. Thaler, Energy flow polynomials: A complete linear basis for jet substructure

Original

2018

Later among the works it cites.

F. A. Dreyer, G. P. Salam, and G. Soyez, The Lund Jet Plane

2018

Later among the works it cites.

M. Dasgupta, F. A. Dreyer, K. Hamilton, P. F. Monni, and G. P. Salam, Logarithmic accuracy of parton showers: a fixed-order study

2018

Later among the works it cites.

Springer International Publishing, Cham, 2018

C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, “A survey on deep transfer learning,” in Artificial Neural Networks and Machine Learning – ICANN 2018 · 2018

Later among the works it cites.

T. Heimel, G. Kasieczka, T. Plehn, and J. M. Thompson, QCD or What?

2019

Later among the works it cites.

A. De Simone and T. Jacques, Guiding New Physics Searches with Unsupervised Learning

2019

Later among the works it cites.

R. T. D’Agnolo and A. Wulzer, Learning New Physics from a Machine

2019

Later among the works it cites.

G. Louppe, K. Cho, C. Becot, and K. Cranmer, QCD-Aware Recursive Neural Networks for Jet Physics

2019

Later among the works it cites.

A. J. Larkoski, I. Moult, and B. Nachman, Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning

2019

Later among the works it cites.

Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, and J. M. Solomon, Dynamic Graph CNN for Learning on Point Clouds

2019

Later among the works it cites.

Curran Associates, Inc., 2019

A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, “Pytorch: An imperative style, high-performance deep learning library,” in Advances in Neural Information Processing Systems 32 · 2019

Later among the works it cites.

06, 2020

F. Van der Veken, G. Azzopardi, F. Blanc, L. Coyle, E. Fol, M. Giovannozzi, T. Pieloni, S. Redaelli, L. Rivkin, B. Salvachua, M. Schenk, R. Tomas, and G. Valentino, “Application of machine learning techniques at the CERN Large Hadron Collider,” · 2020

Later among the works it cites.

G. Kasieczka, S. Marzani, G. Soyez, and G. Stagnitto, Towards machine learning analytics for jet substructure

2020

Later among the works it cites.

J. A. Aguilar-Saavedra, F. R. Joaquim, and J. F. Seabra, Mass Unspecific Supervised Tagging (MUST) for boosted jets

2021

Later among the works it cites.

G. Kasieczka et al

2021

Later among the works it cites.

C. K. Khosa and S. Marzani, Higgs boson tagging with the Lund jet plane

2021

Later among the works it cites.

F. Dreyer and H. Qu, LundNet v1.0.0

2021

Later among the works it cites.

S. Alioli, C. W. Bauer, A. Broggio, A. Gavardi, S. Kallweit, M. A. Lim, R. Nagar, D. Napoletano, and L. Rottoli, Matching NNLO predictions to parton showers using N3LL color-singlet transverse momentum resummation in geneva

2021

Later among the works it cites.

S. Prestel, Matching N3LO QCD calculations to parton showers

2021

Later among the works it cites.