Graph Neural Networks in Particle Physics

Abstract

Particle physics is a branch of science aiming at discovering the fundamental laws of matter and forces. Graph neural networks are trainable functions which operate on graphs---sets of elements and their pairwise relations---and are a central method within the broader field of geometric deep learning. They are very expressive and have demonstrated superior performance to other classical deep learning approaches in a variety of domains. The data in particle physics are often represented by sets and graphs and as such, graph neural networks offer key advantages. Here we review various applications of graph neural networks in particle physics, including different graph constructions, model architectures and learning objectives, as well as key open problems in particle physics for which graph neural networks are promising.

arXiv comment29 pages, 11 figures, submitted to Machine Learning: Science and Technology, Focus on Machine Learning for Fundamental Physics collection

References in corpus (21)

• Deep Learning in Neural Networks: An Overview
• Geometric deep learning: going beyond Euclidean data
• Machine learning and the physical sciences
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• ParticleNet: Jet Tagging via Particle Clouds
• Deep Learning and its Application to LHC Physics
• Pileup Per Particle Identification
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Deep-learning Top Taggers or The End of QCD?
• Energy Flow Networks: Deep Sets for Particle Jets
• Deep-learned Top Tagging with a Lorentz Layer
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Machine and Deep Learning Applications in Particle Physics
• Pulling Out All the Tops with Computer Vision and Deep Learning
• JEDI-net: a jet identification algorithm based on interaction networks
• QCD-Aware Recursive Neural Networks for Jet Physics
• ABCNet: An attention-based method for particle tagging
• Boosting $H\to b\bar{b}$ with Machine Learning
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Probing stop pair production at the LHC with graph neural networks
• Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC

Cited by in corpus (71)

• Combinatorial Optimization with Physics-Inspired Graph Neural Networks
• Finding New Physics without learning about it: Anomaly Detection as a tool for Searches at Colliders
• MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant Systems for Machine Learning
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• Graph Neural Networks Accelerated Molecular Dynamics
• Thermodynamics-informed graph neural networks
• Charged particle tracking via edge-classifying interaction networks
• Symmetries, Safety, and Self-Supervision
• Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
• Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
• Graph Neural Networks for Charged Particle Tracking on FPGAs
• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Quantum Machine Learning for $b$-jet charge identification
• Reconstructing particles in jets using set transformer and hypergraph prediction networks
• Lorentz group equivariant autoencoders
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Bayesian graph convolutional neural networks via tempered MCMC
• Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
• HHH Whitepaper
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• Secondary Vertex Finding in Jets with Neural Networks
• Machine Learning for Particle Flow Reconstruction at CMS
• Invisible Higgs search through Vector Boson Fusion: A deep learning approach
• Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• A Systematic Comparison Study on Hyperparameter Optimisation of Graph Neural Networks for Molecular Property Prediction
• Graph Kernel Neural Networks
• Photon Reconstruction in the Belle II Calorimeter Using Graph Neural Networks
• Classification and reconstruction of optical quantum states with deep neural networks
• Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter
• Jet Discrimination with Quantum Complete Graph Neural Network
• Does Lorentz-symmetric design boost network performance in jet physics?
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Semi-supervised Graph Neural Networks for Pileup Noise Removal
• Ultrafast jet classification on FPGAs for the HL-LHC
• Real-time Graph Building on FPGAs for Machine Learning Trigger Applications in Particle Physics
• Comparing Point Cloud Strategies for Collider Event Classification
• Heterogeneous Graph Neural Network for Identifying Hadronically Decayed Tau Leptons at the High Luminosity LHC
• A Comparison Between Invariant and Equivariant Classical and Quantum Graph Neural Networks
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• Using Machine Learning to Improve Neutron Identification in Water Cherenkov Detectors
• Unsupervised Event Classification with Graphs on Classical and Photonic Quantum Computers
• Unsupervised and lightly supervised learning in particle physics
• Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics
• Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks
• 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
• End-to-End Multi-Track Reconstruction using Graph Neural Networks at Belle II
• Partition Pooling for Convolutional Graph Network Applications in Particle Physics
• Collaborative Goal Tracking of Multiple Mobile Robots Based on Geometric Graph Neural Network
• Learning interactions between Rydberg atoms
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Jet energy calibration with deep learning as a Kubeflow pipeline
• Transforming jet flavour tagging at ATLAS
• Riemannian Data preprocessing in Machine Learning to focus on QCD color structure
• PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
• From strange-quark tagging to fragmentation tagging with machine learning
• MACK: Mismodeling Addressed with Contrastive Knowledge
• Inferring halo masses with Graph Neural Networks
• Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• Segmentation of EM showers for neutrino experiments with deep graph neural networks
• A case study of sending graph neural networks back to the test bench for applications in high-energy particle physics
• Tagging fully hadronic exotic decays of the vectorlike $\mathbf{B}$ quark using a graph neural network
• Fisher information flow in artificial neural networks
• TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Era
• Real-time graph neural networks on FPGAs for the Belle II electromagnetic calorimeter
• Strong CWoLa: Binary Classification Without Background Simulation
• Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction
• jBOT: Semantic Jet Representation Clustering Emerges from Self-Distillation