Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Towards a realistic track reconstruction algorithm based on graph neural networks for the HL-LHCEPJ Web of Conferences, 2021
- MLaaS4HEP: Machine Learning as a Service for HEPComputing and Software for Big Science, 2021
- Overhaul and installation of the ICARUS-T600 liquid argon TPC electronics for the FNAL Short Baseline Neutrino programJournal of Instrumentation, 2021
- Siamese Neural Networks: An Overview2020
- The Tracking Machine Learning Challenge: Accuracy Phase2019
- Gpu-Based Online Track Reconstruction for the Alice Tpc in Run 3 With Continuous Read-OutEPJ Web of Conferences, 2019
- The HEP.TrkX Project: Deep Learning for Particle TrackingJournal of Physics: Conference Series, 2018
- Comparison of two hardware-based hit filtering methods for trackers in high-pileup environmentsJournal of Instrumentation, 2018
- The HEP.TrkX Project: deep neural networks for HL-LHC online and offline trackingEPJ Web of Conferences, 2017
- Parallel track reconstruction in CMS using the cellular automaton approachJournal of Physics: Conference Series, 2014