ABCNet: An attention-based method for particle tagging

Abstract

In high energy physics, graph-based implementations have the advantage of treating the input data sets in a similar way as they are collected by collider experiments. To expand on this concept, we propose a graph neural network enhanced by attention mechanisms called ABCNet. To exemplify the advantages and flexibility of treating collider data as a point cloud, two physically motivated problems are investigated: quark-gluon discrimination and pileup reduction. The former is an event-by-event classification while the latter requires each reconstructed particle to receive a classification score. For both tasks ABCNet shows an improved performance compared to other algorithms available.

arXiv comment13 pages, 5 figures

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• ParticleNet: Jet Tagging via Particle Clouds
• Pileup Per Particle Identification
• Deep learning in color: towards automated quark/gluon jet discrimination
• Energy Flow Networks: Deep Sets for Particle Jets
• Parameterized Machine Learning for High-Energy Physics
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• JEDI-net: a jet identification algorithm based on interaction networks
• Pileup Mitigation with Machine Learning (PUMML)
• SoftKiller, a particle-level pileup removal method
• Probing stop pair production at the LHC with graph neural networks
• Novel deep learning methods for track reconstruction
• GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
• Graph Neural Networks for IceCube Signal Classification

Cited by in corpus (57)

• Graph Neural Networks in Particle Physics
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Anomaly detection with Convolutional Graph Neural Networks
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• Machine Learning for Anomaly Detection in Particle Physics
• Point Cloud Transformers applied to Collider Physics
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Mapping Machine-Learned Physics into a Human-Readable Space
• Unsupervised clustering for collider physics
• Review of searches for vector-like quarks, vector-like leptons, and heavy neutral leptons in proton-proton collisions at $\sqrt{s}$ = 13 TeV at the CMS experiment
• Symmetries, Safety, and Self-Supervision
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Jet Flavour Tagging for Future Colliders with Fast Simulation
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• Explainable Equivariant Neural Networks for Particle Physics: PELICAN
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Probing triple Higgs coupling with machine learning at the LHC
• Pile-Up Mitigation using Attention
• Unbinned Deep Learning Jet Substructure Measurement in High $Q^2$ ep collisions at HERA
• Precision-Machine Learning for the Matrix Element Method
• Secondary Vertex Finding in Jets with Neural Networks
• Machine Learning for Particle Flow Reconstruction at CMS
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Jet tagging algorithm of graph network with HaarPooling message passing
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• GPU coprocessors as a service for deep learning inference in high energy physics
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Tagging more quark jet flavours at FCC-ee at 91 GeV with a transformer-based neural network
• Search for pair-produced vector-like leptons in final states with third-generation leptons and at least three b quark jets in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Jet Tagging with More-Interaction Particle Transformer
• Maximum performance of strange-jet tagging at hadron colliders
• Does Lorentz-symmetric design boost network performance in jet physics?
• BIP: Boost Invariant Polynomials for Efficient Jet Tagging
• Semi-supervised Graph Neural Networks for Pileup Noise Removal
• Real-time Graph Building on FPGAs for Machine Learning Trigger Applications in Particle Physics
• Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks
• Comparing Point Cloud Strategies for Collider Event Classification
• Is infrared-collinear safe information all you need for jet classification?
• A Comparison Between Invariant and Equivariant Classical and Quantum Graph Neural Networks
• Hypergraphs in LHC Phenomenology -- The Next Frontier of IRC-Safe Feature Extraction
• Optimal transport for a novel event description at hadron colliders
• Search for vector-like leptons at a Muon Collider
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
• Semi-supervised permutation invariant particle-level anomaly detection
• Top-philic Machine Learning
• Quark-versus-gluon tagging in CMS Open Data with CWoLa and TopicFlow
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Particle-level transformers for 95 GeV Higgs boson searches at future $e^{+}{e}^{-}$ Higgs factories
• Distributed training and scalability for the particle clustering method UCluster
• Identifying the Quantum Properties of Hadronic Resonances using Machine Learning
• OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
• Tagging fully hadronic exotic decays of the vectorlike $\mathbf{B}$ quark using a graph neural network
• Explaining machine-learned particle-flow reconstruction
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction
• Distilling particle knowledge for fast reconstruction at high-energy physics experiments