8–12 Sept 2025
Hamburg, Germany
Europe/Berlin timezone

Developments of GNN Track Reconstruction for the ATLAS ITk Detector

8 Sept 2025, 14:30
20m
ESA B

ESA B

Oral Track 2: Data Analysis - Algorithms and Tools Track 2: Data Analysis - Algorithms and Tools

Speaker

Jay Chan (Lawrence Berkeley National Lab. (US))

Description

Track reconstruction is a cornerstone of modern collider experiments, and the HL-LHC ITk upgrade for ATLAS poses new challenges with its increased silicon hit clusters and strict throughput requirements. Deep learning approaches compare favorably with traditional combinatorial ones — as shown by the GNN4ITk project, a geometric learning tracking pipeline that achieves competitive physics performance at sub-second inference times. In this contribution, we evaluate a range of pipeline configurations and machine learning inference strategies that further improve track reconstruction at lower latencies. We present benchmarks for latency, throughput, memory usage, and power consumption across these pipelines. New developments include improved GPU-based module map performance and memory optimizations; model enhancements through pruning, quantization and advanced compilation techniques used in industry; and a custom graph segmentation approach. These upgrades allow the pipeline to target trigger-level track reconstruction in certain conditions. We also discuss improvements in track fitting, integrations into traditional-learned hybrid pipelines, GNN-based seeding, triplet-wise processing of cluster features, and production readiness with inference-as-a-service.

Significance

This is a major update to the ML-based tracking chain for ATLAS upgrade, that shows for the first time competitive physics performance with traditional techniques, as well as computational improvements, reducing latency by around 3x compared with previous reports.

References

https://indico.cern.ch/event/1338689/contributions/6011080/
https://cds.cern.ch/record/2871986/files/ATL-SOFT-PROC-2023-038.pdf

Experiment context, if any ATLAS experiment

Authors

Aleksandra Poreba (CERN / Ruprecht Karls Universitaet Heidelberg (DE)) Alexis Vallier (L2I Toulouse, CNRS/IN2P3, UT3) Alina Lazar (Youngstown State University (US)) Benjamin Huth (CERN) Dr Christophe Collard (Laboratoire des 2 Infinis - Toulouse, CNRS / Univ. Paul Sabatier) Daniel Thomas Murnane (Niels Bohr Institute, University of Copenhagen) Heberth Torres (L2I Toulouse, CNRS/IN2P3, UT3) Jackson Carl Burzynski (Simon Fraser University (CA)) Jan Stark (Laboratoire des 2 Infinis - Toulouse, CNRS / Univ. Paul Sabatier (FR)) Jared Burleson Jay Chan (Lawrence Berkeley National Lab. (US)) Levi Condren (University of California Irvine (US)) Mark Neubauer (Univ. Illinois at Urbana Champaign (US)) Miles Cochran-Branson (University of Washington (US)) Minh-Tuan Pham (University of Wisconsin Madison (US)) Paolo Calafiura (Lawrence Berkeley National Lab. (US)) Pierfrancesco Butti (CERN) Prachi Atmasiddha (University of Pennsylvania) Santosh Parajuli (Univ. Illinois at Urbana Champaign (US)) Sebastian Dittmeier (Ruprecht-Karls-Universitaet Heidelberg (DE)) Sylvain Caillou (Centre National de la Recherche Scientifique (FR)) Warren Guerin (L2I Toulouse, CNRS/IN2P3, UT3) Xiangyang Ju (Lawrence Berkeley National Lab. (US)) Yuan-Tang Chou (University of Washington (US))

Presentation materials