Graph Neural Networks for Particle Tracking and Reconstruction

Abstract

Machine learning methods have a long history of applications in high energy physics (HEP). Recently, there is a growing interest in exploiting these methods to reconstruct particle signatures from raw detector data. In order to benefit from modern deep learning algorithms that were initially designed for computer vision or natural language processing tasks, it is common practice to transform HEP data into images or sequences. Conversely, graph neural networks (GNNs), which operate on graph data composed of elements with a set of features and their pairwise connections, provide an alternative way of incorporating weight sharing, local connectivity, and specialized domain knowledge. Particle physics data, such as the hits in a tracking detector, can generally be represented as graphs, making the use of GNNs natural. In this chapter, we recapitulate the mathematical formalism of GNNs and highlight aspects to consider when designing these networks for HEP data, including graph construction, model architectures, learning objectives, and graph pooling. We also review promising applications of GNNs for particle tracking and reconstruction in HEP and summarize the outlook for their deployment in current and future experiments.

44 pages, 20 figures. Submitted for review. To appear in "Artificial Intelligence for Particle Physics", World Scientific Publishing

Cited by in corpus (20)

• Applications and Techniques for Fast Machine Learning in Science
• Graph Neural Networks for Charged Particle Tracking on FPGAs
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• The Tracking Machine Learning challenge : Throughput phase
• HHH Whitepaper
• A deep learning method for the trajectory reconstruction of cosmic rays with the DAMPE mission
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Real-time Graph Building on FPGAs for Machine Learning Trigger Applications in Particle Physics
• Heterogeneous Graph Neural Network for Identifying Hadronically Decayed Tau Leptons at the High Luminosity LHC
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Distributed Training and Optimization Of Neural Networks
• Accelerating Graph-based Tracking Tasks with Symbolic Regression
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• On-line computing challenges: detector and readout requirements
• Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection
• Segmentation of EM showers for neutrino experiments with deep graph neural networks
• TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Era
• Physics-informed neural network (PINN) modeling of charged particle multiplicity using the two-component framework in heavy-ion collisions: A comparison with data-driven neural networks
• Real-time graph neural networks on FPGAs for the Belle II electromagnetic calorimeter
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction