FAIR AI models in high energy physics

被引：1

作者：

Duarte, Javier ^{[1
]}

Li, Haoyang ^{[1
]}

Roy, Avik ^{[2
]}

Zhu, Ruike ^{[2
,3
]}

Huerta, E. A. ^{[3
,4
]}

Diaz, Daniel ^{[1
]}

Harris, Philip ^{[5
]}

Kansal, Raghav ^{[1
]}

Katz, Daniel S. ^{[2
]}

Kavoori, Ishaan H. ^{[1
]}

Kindratenko, Volodymyr V. ^{[2
]}

Mokhtar, Farouk ^{[1
,6
]}

Neubauer, Mark S. ^{[2
]}

Eon Park, Sang ^{[5
]}

Quinnan, Melissa ^{[1
]}

Rusack, Roger ^{[7
]}

Zhao, Zhizhen ^{[2
]}

机构：

[1] Univ Calif San Diego, La Jolla, CA 92093 USA

[2] Univ Illinois, Urbana, IL 61801 USA

[3] Argonne Natl Lab, Lemont, IL 60439 USA

[4] Univ Chicago, Chicago, IL 60637 USA

[5] MIT, Cambridge, MA 02139 USA

[6] Halicioglu Data Sci Inst, La Jolla, CA 92093 USA

[7] Univ Minnesota, Minneapolis, MN 55405 USA

来源：

MACHINE LEARNING-SCIENCE AND TECHNOLOGY | 2023年 / 4卷 / 04期

基金：

美国国家科学基金会;

关键词：

FAIR; AI; high energy physics; Higgs boson; ML;

D O I：

10.1088/2632-2153/ad12e3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The findable, accessible, interoperable, and reusable (FAIR) data principles provide a framework for examining, evaluating, and improving how data is shared to facilitate scientific discovery. Generalizing these principles to research software and other digital products is an active area of research. Machine learning models-algorithms that have been trained on data without being explicitly programmed-and more generally, artificial intelligence (AI) models, are an important target for this because of the ever-increasing pace with which AI is transforming scientific domains, such as experimental high energy physics (HEP). In this paper, we propose a practical definition of FAIR principles for AI models in HEP and describe a template for the application of these principles. We demonstrate the template's use with an example AI model applied to HEP, in which a graph neural network is used to identify Higgs bosons decaying to two bottom quarks. We report on the robustness of this FAIR AI model, its portability across hardware architectures and software frameworks, and its interpretability.

引用

页数：21

共 95 条

[1] Observation of H → b(b)over-bar decays and V H production with the ATLAS detector [J].

Aaboud, M. ;

Aad, G. ;

Abbott, B. ;

Abdinov, O. ;

Abeloos, B. ;

Abhayasinghe, D. K. ;

Abidi, S. H. ;

AbouZeid, O. S. ;

Abraham, N. L. ;

Abramowicz, H. ;

Abreu, H. ;

Abulaiti, Y. ;

Acharya, B. S. ;

Adachi, S. ;

Adam, L. ;

Adamczyk, L. ;

Adelman, J. ;

Adersberger, M. ;

Adiguzel, A. ;

Adye, T. ;

Affolder, A. A. ;

Afik, Y. ;

Agheorghiesei, C. ;

Aguilar-Saavedra, J. A. ;

Ahmadov, F. ;

Aielli, G. ;

Akatsuka, S. ;

Akesson, T. P. A. ;

Akilli, E. ;

Akimov, A. V. ;

Alberghi, G. L. ;

Albert, J. ;

Albicocco, P. ;

AlconadaVerzini, M. J. ;

Alderweireldt, S. ;

Aleksa, M. ;

Aleksandrov, I. N. ;

Alexa, C. ;

Alexandre, D. ;

Alexopoulos, T. ;

Alhroob, M. ;

Ali, B. ;

Alimonti, G. ;

Alison, J. ;

Alkire, S. P. ;

Allaire, C. ;

Allbrooke, B. M. M. ;

Allen, B. W. ;

Allport, P. P. ;

Aloisio, A. .

PHYSICS LETTERS B, 2018, 786 :59-86

[2] Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC [J].

Aad, G. ;

Abajyan, T. ;

Abbott, B. ;

Abdallah, J. ;

Khalek, S. Abdel ;

Abdelalim, A. A. ;

Abdinov, O. ;

Aben, R. ;

Abi, B. ;

Abolins, M. ;

AbouZeid, U. S. ;

Abramowicz, H. ;

Abreu, H. ;

Acharya, B. S. ;

Adamczyk, L. ;

Adams, D. L. ;

Addy, T. N. ;

Adelman, J. ;

Adomeit, S. ;

Adragna, P. ;

Adye, T. ;

Aefsky, S. ;

Aguilar-Saavedra, J. A. ;

Agustoni, M. ;

Aharrouche, M. ;

Ahlen, S. P. ;

Ahles, F. ;

Ahmad, A. ;

Ahsan, M. ;

Aielli, G. ;

Akdogan, T. ;

Akesson, T. P. A. ;

Akimoto, G. ;

Akimov, A. V. ;

Alam, M. S. ;

Alam, M. A. ;

Albert, J. ;

Albrand, S. ;

Aleksa, M. ;

Aleksandrov, I. N. ;

Alessandria, F. ;

Alexa, C. ;

Alexander, G. ;

Alexandre, G. ;

Alexopoulos, T. ;

Alhroob, M. ;

Aliev, M. ;

Alimonti, G. ;

Alison, J. ;

Allbrooke, B. M. M. .

PHYSICS LETTERS B, 2012, 716 (01) :1-29

[3]

Abadi M., 2015, TENSORFLOW LARGE SCA

[4] Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation [J].

Agarwal, Garvita ;

Hay, Lauren ;

Iashvili, Ia ;

Mannix, Benjamin ;

McLean, Christine ;

Morris, Margaret ;

Rappoccio, Salvatore ;

Schubert, Ulrich .

JOURNAL OF HIGH ENERGY PHYSICS, 2021, 2021 (05)

[5]

AI Model Share Project, 2022, AI model share platform

[6] On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation [J].

Bach, Sebastian ;

Binder, Alexander ;

Montavon, Gregoire ;

Klauschen, Frederick ;

Mueller, Klaus-Robert ;

Samek, Wojciech .

PLOS ONE, 2015, 10 (07)

[7]

Bai J., 2017, OPEN NEURAL NETWORK

[8] Introducing the FAIR Principles for research software [J].

Barker, Michelle ;

Hong, Neil P. Chue ;

Katz, Daniel S. ;

Lamprecht, Anna-Lena ;

Martinez-Ortiz, Carlos ;

Psomopoulos, Fotis ;

Harrow, Jennifer ;

Castro, Leyla Jael ;

Gruenpeter, Morane ;

Martinez, Paula Andrea ;

Honeyman, Tom .

SCIENTIFIC DATA, 2022, 9 (01)

[9]

Battaglia P W., 2016, Advances in neural information processing systems, V29, P2

[10]

Benelli G., 2022, arXiv

← 1 2 3 4 5 6 7 8 9 10 →