Charged particle tracking via edge-classifying interaction networks

21 May 2021, 17:00
30m
Long talk Offline Computing Fri PM Plenaries

Speaker

Gage DeZoort (Princeton University (US))

Description

Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well-suited to address a variety of recon- struction problems in HEP. In particular, tracker events are naturally repre- sented as graphs by identifying hits as nodes and track segments as edges; given a set of hypothesized edges, edge-classifying GNNs predict which rep- resent real track segments. In this work, we adapt the physics-motivated Inter- action Network (IN) GNN to the problem of charged-particle tracking in the high-pileup conditions expected at the HL-LHC. We demonstrate the IN’s ex- cellent edge-classification accuracy and tracking efficiency through a suite of measurements at each stage of GNN-based tracking: graph construction, edge- classification, and track building. Notably, the proposed IN architecture is sub- stantially smaller than previously studied GNN tracking architectures; this type of reduction in size critical for enabling GNN-based tracking in constrained computing environments. Furthermore, the IN is easily expressed as a set of matrix operations, making it a promising candidate for acceleration via hetero- geneous computing resources.

Primary authors

Savannah Jennifer Thais (Princeton University (US)) Gage DeZoort (Princeton University (US)) Isobel Ojalvo (Princeton University (US)) Peter Elmer (Princeton University (US)) Markus Julian Atkinson (Univ. Illinois at Urbana Champaign (US)) Mark Neubauer (Univ. Illinois at Urbana Champaign (US)) Javier Mauricio Duarte (Univ. of California San Diego (US)) Vesal Razavimaleki (Univ. of California San Diego (US))

Presentation materials