An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging

Abstract

Deep learning methods have been increasingly adopted to study jets in particle physics. Since symmetry-preserving behavior has been shown to be an important factor for improving the performance of deep learning in many applications, Lorentz group equivariance - a fundamental spacetime symmetry for elementary particles - has recently been incorporated into a deep learning model for jet tagging. However, the design is computationally costly due to the analytic construction of high-order tensors. In this article, we introduce LorentzNet, a new symmetry-preserving deep learning model for jet tagging. The message passing of LorentzNet relies on an efficient Minkowski dot product attention. Experiments on two representative jet tagging benchmarks show that LorentzNet achieves the best tagging performance and improves significantly over existing state-of-the-art algorithms. The preservation of Lorentz symmetry also greatly improves the efficiency and generalization power of the model, allowing LorentzNet to reach highly competitive performance when trained on only a few thousand jets. Code and models are available at \url{https://github.com/sdogsq/LorentzNet-release}.

22 pages, 3 figures, and 7 tables

References in corpus (16)

• Boosted objects: a probe of beyond the Standard Model physics
• Jet Flavour Classification Using DeepJet
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Sampling using $SU(N)$ gauge equivariant flows
• Lorentz Group Equivariant Neural Network for Particle Physics
• Point Cloud Transformers applied to Collider Physics
• Equivariant Energy Flow Networks for Jet Tagging
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• Quarks and gluons in the Lund plane
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• LieTransformer: Equivariant self-attention for Lie Groups
• Scalars are universal: Equivariant machine learning, structured like classical physics
• Reconstructing boosted Higgs jets from event image segmentation
• Particle Convolution for High Energy Physics

Cited by in corpus (60)

• Exploring QCD matter in extreme conditions with Machine Learning
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Explainable Equivariant Neural Networks for Particle Physics: PELICAN
• Lorentz group equivariant autoencoders
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
• Unbinned Deep Learning Jet Substructure Measurement in High $Q^2$ ep collisions at HERA
• Boosting mono-jet searches with model-agnostic machine learning
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
• Jet tagging algorithm of graph network with HaarPooling message passing
• A Lorentz-Equivariant Transformer for All of the LHC
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Data-Directed Search for New Physics based on Symmetries of the SM
• Jet Tagging with More-Interaction Particle Transformer
• Searches for new physics with boosted top quarks in the MadAnalysis 5 and Rivet frameworks
• Jet Discrimination with Quantum Complete Graph Neural Network
• Does Lorentz-symmetric design boost network performance in jet physics?
• BIP: Boost Invariant Polynomials for Efficient Jet Tagging
• Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks
• Ultrafast jet classification on FPGAs for the HL-LHC
• Equivariant, Safe and Sensitive -- Graph Networks for New Physics
• Is infrared-collinear safe information all you need for jet classification?
• Comparing Point Cloud Strategies for Collider Event Classification
• A Comparison Between Invariant and Equivariant Classical and Quantum Graph Neural Networks
• Advancing Tools for Simulation-Based Inference
• Accuracy versus precision in boosted top tagging with the ATLAS detector
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• Hypergraphs in LHC Phenomenology -- The Next Frontier of IRC-Safe Feature Extraction
• Interpretable deep learning models for the inference and classification of LHC data
• Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics
• Jet Classification Using High-Level Features from Anatomy of Top Jets
• Automatic detection of boosted Higgs boson and top quark jets in an event image
• Unveiling the Secrets of New Physics Through Top Quark Tagging
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments
• A rotation-equivariant graph neural network for learning hadronic SMEFT effects
• Tau lepton identification and reconstruction: a new frontier for jet-tagging ML algorithms
• Semi-supervised permutation invariant particle-level anomaly detection
• Probing sub-TeV Higgsinos aided by a ML-based top tagger in the context of Trilinear RPV SUSY
• A unified machine learning approach for reconstructing hadronically decaying tau leptons
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Equivariant neural networks for robust $\text{CP}$ observables
• Learning Broken Symmetries with Approximate Invariance
• BitHEP -- The Limits of Low-Precision ML in HEP
• Particle-level transformers for 95 GeV Higgs boson searches at future $e^{+}{e}^{-}$ Higgs factories
• Jet Reconstruction with Mamba Networks in Collider Events
• Jet Rotational Metrics
• OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
• Thermodynamics of Barrow Einstein-power-Yang-Mills AdS black hole in the restricted phase space
• Graph theory inspired anomaly detection at the LHC
• Vision Transformers for End-to-End Quark-Gluon Jet Classification from Calorimeter Images
• Deep learning for jet modification in the presence of the QGP background
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction
• Enhancing generalization in high energy physics using white-box adversarial attacks
• Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features
• jBOT: Semantic Jet Representation Clustering Emerges from Self-Distillation
• Strong CWoLa: Binary Classification Without Background Simulation
• Large Language Models -- the Future of Fundamental Physics?
• Distilling particle knowledge for fast reconstruction at high-energy physics experiments