End-to-end multi-particle reconstruction in high occupancy imaging calorimeters with graph neural networks

no code implementations • 4 Apr 2022 • Shah Rukh Qasim, Nadezda Chernyavskaya, Jan Kieseler, Kenneth Long, Oleksandr Viazlo, Maurizio Pierini, Raheel Nawaz

We present an end-to-end reconstruction algorithm to build particle candidates from detector hits in next-generation granular calorimeters similar to that foreseen for the high-luminosity upgrade of the CMS detector.

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

no code implementations • 8 Aug 2020 • Yutaro Iiyama, Gianluca Cerminara, Abhijay Gupta, Jan Kieseler, Vladimir Loncar, Maurizio Pierini, Shah Rukh Qasim, Marcel Rieger, Sioni Summers, Gerrit Van Onsem, Kinga Wozniak, Jennifer Ngadiuba, Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Dylan Rankin, Sergo Jindariani, Mia Liu, Kevin Pedro, Nhan Tran, Edward Kreinar, Zhenbin Wu

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering.

Clustering Jet Tagging +1

Rethinking Table Recognition using Graph Neural Networks

5 code implementations • 31 May 2019 • Shah Rukh Qasim, Hassan Mahmood, Faisal Shafait

In this paper, we propose an architecture based on graph networks as a better alternative to standard neural networks for table recognition.

Table Recognition

Learning representations of irregular particle-detector geometry with distance-weighted graph networks

3 code implementations • 21 Feb 2019 • Shah Rukh Qasim, Jan Kieseler, Yutaro Iiyama, Maurizio Pierini

We explore the use of graph networks to deal with irregular-geometry detectors in the context of particle reconstruction.

Clustering Representation Learning