Title: Semi-supervised graph neural networks for pileup noise removal

Journal Article · · European Physical Journal. C, Particles and Fields (Online)

Abstract The high instantaneous luminosity of the CERN Large Hadron Collider leads to multiple proton–proton interactions in the same or nearby bunch crossings (pileup). Advanced pileup mitigation algorithms are designed to remove this noise from pileup particles and improve the performance of crucial physics observables. This study implements a semi-supervised graph neural network for particle-level pileup noise removal, by identifying individual particles produced from pileup. The graph neural network is firstly trained on charged particles with known labels, which can be obtained from detector measurements on data or simulation, and then inferred on neutral particles for which such labels are missing. This semi-supervised approach does not depend on the neutral particle pileup label information from simulation, and thus allows us to perform training directly on experimental data. The performance of this approach is found to be consistently better than widely-used domain algorithms and comparable to the fully-supervised training using simulation truth information. The study serves as the first attempt at applying semi-supervised learning techniques to pileup mitigation, and opens up a new direction of fully data-driven machine learning pileup mitigation studies.

Research Organization:
Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
Sponsoring Organization:
National Science Foundation (NSF); USDOE; USDOE Office of Science (SC), High Energy Physics (HEP)
Grant/Contract Number:
AC02-07CH11359; SC0007884
OSTI ID:
1922868
Report Number(s):
FERMILAB-PUB-22-235-PPD-SCD; arXiv:2203.15823; 99; PII: 11083
Journal Information:
European Physical Journal. C, Particles and Fields (Online), Journal Name: European Physical Journal. C, Particles and Fields (Online) Journal Issue: 1 Vol. 83; ISSN 1434-6052
Publisher:
Springer Science + Business MediaCopyright Statement
Country of Publication:
Germany
Language:
English

References (35)

Energy flow networks: deep sets for particle jets journal January 2019
DELPHES 3: a modular framework for fast simulation of a generic collider experiment journal February 2014
Interleaved parton showers and tuning prospects journal March 2011
Particle-level pileup subtraction for jets and jet shapes journal June 2014
Pileup per particle identification journal October 2014
Pileup Mitigation with Machine Learning (PUMML) journal December 2017
Geant4—a simulation toolkit
  • Agostinelli, S.; Allison, J.; Amako, K.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 506, Issue 3 https://doi.org/10.1016/S0168-9002(03)01368-8
journal July 2003
An introduction to PYTHIA 8.2 journal June 2015
Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC journal September 2012
Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC journal September 2012
Community detection in graphs journal February 2010
Deep learning journal May 2015
The anti- k t jet clustering algorithm journal April 2008
Quantifying the performance of jet definitions for kinematic reconstruction at the LHC journal December 2008
Particle-flow reconstruction and global event description with the CMS detector journal October 2017
Performance of missing transverse momentum reconstruction in proton-proton collisions at √ s = 13 TeV using the CMS detector journal July 2019
Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques journal June 2020
Pileup mitigation at CMS in 13 TeV data journal September 2020
Description and performance of track and primary-vertex reconstruction with the CMS tracker journal October 2014
Graph neural networks in particle physics journal January 2021
Pile-up mitigation using attention journal June 2022
Jet tagging via particle clouds journal March 2020
Jet cleansing: Separating data from secondary collision induced radiation at high luminosity journal September 2014
Use of charged-track information to subtract neutral pileup journal July 2015
Community detection algorithms: A comparative analysis journal November 2009
SoftKiller, a particle-level pileup removal method journal February 2015
Performance of the ATLAS track reconstruction algorithms in dense environments in LHC Run 2 journal October 2017
Performance of missing transverse momentum reconstruction with the ATLAS detector using proton–proton collisions at $$\sqrt{s}=13~\hbox {TeV}$$ s = 13 TeV journal November 2018
Learning representations of irregular particle-detector geometry with distance-weighted graph networks journal July 2019
MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks journal May 2021
Jet energy scale and resolution measured in proton–proton collisions at $$\sqrt{s}=13$$ TeV with the ATLAS detector journal August 2021
Precision luminosity measurement in proton–proton collisions at $$\sqrt{s} = 13\,\hbox {TeV}$$ in 2015 and 2016 at CMS journal September 2021
Pileup mitigation at the Large Hadron Collider with graph neural networks journal July 2019
ABCNet: an attention-based method for particle tagging journal June 2020
The High Luminosity Large Hadron Collider: The New Machine for Illuminating the Mysteries of the Universe book February 2015

Similar Records

Pileup Mitigation with Machine Learning (PUMML)
Journal Article · 2017 · Journal of High Energy Physics (Online) · OSTI ID:1485069

Xenon signal denoising via supervised, semi-supervised, and unsupervised models
Journal Article · 2026 · European Physical Journal. C, Particles and Fields (Online) · OSTI ID:3410695

SNM Radiation Signature Classification Using Different Semi-Supervised Machine Learning Models
Journal Article · 2023 · Journal of Nuclear Engineering · OSTI ID:1988203