Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC

Abstract

The application of machine learning (ML) in high energy physics (HEP), specifically in heavy-flavor jet tagging at Large Hadron Collider (LHC) experiments, has experienced remarkable growth and innovation in the past decade. This review provides a detailed examination of current and past ML techniques in this domain. It starts by exploring various data representation methods and ML architectures, encompassing traditional ML algorithms and advanced deep learning techniques. Subsequent sections discuss specific instances of successful ML applications in jet flavor tagging in the ATLAS and CMS experiments at the LHC, ranging from basic fully-connected layers to graph neural networks employing attention mechanisms. To systematically categorize the advancements over the LHC's three runs, the paper classifies jet tagging algorithms into three generations, each characterized by specific data representation techniques and ML architectures. This classification aims to provide an overview of the chronological evolution in this field. Finally, a brief discussion about anticipated future developments and potential research directions in the field is presented.

38 pages, 2 tables, 1 figure

References in corpus (41)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Jet substructure as a new Higgs search channel at the LHC
• Top-tagging: A Method for Identifying Boosted Hadronic Tops
• A portrait of the Higgs boson by the CMS experiment ten years after the discovery
• Pileup Per Particle Identification
• Classification without labels: Learning from mixed samples in high energy physics
• Gaining (Mutual) Information about Quark/Gluon Discrimination
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• New Angles on Energy Correlation Functions
• ATLAS flavour-tagging algorithms for the LHC Run 2 $pp$ collision dataset
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Pileup Mitigation with Machine Learning (PUMML)
• Measurement of the $c$-jet mistagging efficiency in $t\bar{t}$ events using $pp$ collision data at $\sqrt{s}=13$ TeV collected with the ATLAS detector
• Anomaly detection with Convolutional Graph Neural Networks
• Calibration of the light-flavour jet mistagging efficiency of the $b$-tagging algorithms with $Z$+jets events using 139 ${\mathrm{fb}}^{-1}$ of ATLAS proton-proton collision data at $\sqrt{s}=13$ TeV
• W-jet Tagging: Optimizing the Identification of Boosted Hadronically-Decaying W Bosons
• Lorentz Group Equivariant Neural Network for Particle Physics
• Quark-Gluon tagging with Shower Deconstruction: Unearthing dark matter and Higgs couplings
• Associated jet and subjet rates in light-quark and gluon jet discrimination
• Equivariant Energy Flow Networks for Jet Tagging
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Direct constraint on the Higgs-charm coupling from a search for Higgs boson decays into charm quarks with the ATLAS detector
• Quarks and gluons in the Lund plane
• Search for Higgs boson decay to a charm quark-antiquark pair in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• NormFormer: Improved Transformer Pretraining with Extra Normalization
• A new calibration method for charm jet identification validated with proton-proton collision events at $\sqrt{s}$ = 13 TeV
• Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark
• Identification of b-jets using QCD-inspired observables
• Dynamic Radius Jet Clustering Algorithm
• Search for Higgs boson and observation of Z boson through their decay into a charm quark-antiquark pair in boosted topologies in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• BIP: Boost Invariant Polynomials for Efficient Jet Tagging
• A Wavelet Based Pile-Up Mitigation Method for the LHC Upgrade
• Pileup and Infrared Radiation Annihilation (PIRANHA): A Paradigm for Continuous Jet Grooming
• Improving Robustness of Jet Tagging Algorithms with Adversarial Training
• Hunting for bumps in the margins
• Flavour tagging with graph neural networks with the ATLAS detector

Cited by in corpus (10)

• Tagging more quark jet flavours at FCC-ee at 91 GeV with a transformer-based neural network
• Reconstruction of boosted and resolved multi-Higgs-boson events with symmetry-preserving attention networks
• Machine-Learning Analysis of Radiative Decays to Dark Matter at the LHC
• From strange-quark tagging to fragmentation tagging with machine learning
• Systematically Constructing the Likelihood for Boosted $H\to gg$ Decays
• B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture
• Shedding Light on Dark Matter at the LHC with Machine Learning
• Exploring an image-based $b$-jet tagging method using convolution neural networks
• Tagging ultra-boosted jets at FCC-hh using machine learning techniques
• TIGER: A Topology-Agnostic, Hierarchical Graph Network for Event Reconstruction