Pileup mitigation at the Large Hadron Collider with Graph Neural Networks

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, 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.

12 pages, 11 figures

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• An Introduction to PYTHIA 8.2
• Neural Message Passing for Quantum Chemistry
• Jet substructure as a new Higgs search channel at the LHC
• Particle-flow reconstruction and global event description with the CMS detector
• Gated Graph Sequence Neural Networks
• Pileup Per Particle Identification
• A Convolutional Neural Network Neutrino Event Classifier
• Pileup subtraction for jet shapes
• Pileup Mitigation with Machine Learning (PUMML)
• Jet Cleansing: Pileup Removal at High Luminosity
• On the use of charged-track information to subtract neutral pileup

Cited by in corpus (5)

• The Metric Space of Collider Events
• ABCDisCo: Automating the ABCD Method with Machine Learning
• Quark-Gluon Tagging: Machine Learning vs Detector
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Classifying the Cosmic-Ray Proton and Light Groups on the LHAASO-KM2A Experiment with the Graph Neural Network