Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking

Abstract

The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. Exa.TrkX's tracking pipeline groups detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity Calorimeter. This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS and CMS data. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms. Crucially for future HEP applications, the pipeline benefits significantly from GPU acceleration, and its computational requirements scale close to linearly with the number of particles in the event.

References in corpus (10)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Fast Graph Representation Learning with PyTorch Geometric
• Description and performance of track and primary-vertex reconstruction with the CMS tracker
• Accelerating 3D Deep Learning with PyTorch3D
• Dissecting the Graphcore IPU Architecture via Microbenchmarking
• Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs
• Distributed Training of Graph Convolutional Networks
• Overhaul and Installation of the ICARUS-T600 Liquid Argon TPC Electronics for the FNAL Short Baseline Neutrino Program
• Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers