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.

Point Cloud Transformers applied to Collider Physics

“…Neural network architectures that treat collision events as point clouds have recently grown in number given their state-of-the-art performance when applied to different collider physics problems. A few examples of such applications are jet-tagging [7,8], secondary vertex finding [9], event reconstruction [10][11][12][13], and jet parton assignment [14]. A comprehensive review of the different methods is described in [15].…”

On-line computing challenges: detector and readout requirements

“…In recent years we have witnessed an explosive growth of machine learning techniques in HEP applications. Indeed, there is a strong R&D activity concerning the deployment of machine learning technologies in both off-the-shelf commercial processors and FPGAs with a more limited computing footprint [16,17]. Some examples include: front-end data compression, particle identification with multivariate classifiers, pattern recognition, tracking and reconstruction with neural networks and regression for improved resolution.…”

Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance

“…We propose particle graph autoencoders (PGAEs) based on graph neural networks (GNNs) [7,8] for unsupervised detection of new physics in multijet final states at the LHC. By embedding particle jet showers as a graph, GNNs are able to exploit particle-to-particle relationships to efficiently encode and reconstruct particle-level information within jets.…”