Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking
This work addresses particle tracking for high-energy physics experiments like HL-LHC, but it is incremental as it builds on prior pipeline developments and focuses on validation steps.
The Exa.TrkX project tackled particle tracking in high-energy physics by applying geometric deep learning, achieving tracking efficiency and purity similar to existing algorithms while demonstrating near-linear computational scaling with particle count and significant GPU acceleration benefits.
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.