Hybrid quantum classical graph neural networks for particle track reconstruction

Date

2021-12-01

Author

Tuysuz, Cenk
Rieger, Carla
Novotny, Kristiane
Demirköz, Melahat Bilge
Dobos, Daniel
Potamianos, Karolos
Vallecorsa, Sofia
Vlimant, Jean-Roch
Forster, Richard

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

191
views

0
downloads

The Large Hadron Collider (LHC) at the European Organisation for Nuclear Research (CERN) will be upgraded to further increase the instantaneous rate of particle collisions (luminosity) and become the High Luminosity LHC (HL-LHC). This increase in luminosity will significantly increase the number of particles interacting with the detector. The interaction of particles with a detector is referred to as "hit". The HL-LHC will yield many more detector hits, which will pose a combinatorial challenge by using reconstruction algorithms to determine particle trajectories from those hits. This work explores the possibility of converting a novel graph neural network model, that can optimally take into account the sparse nature of the tracking detector data and their complex geometry, to a hybrid quantum-classical graph neural network that benefits from using variational quantum layers. We show that this hybrid model can perform similar to the classical approach. Also, we explore parametrized quantum circuits (PQC) with different expressibility and entangling capacities, and compare their training performance in order to quantify the expected benefits. These results can be used to build a future road map to further develop circuit-based hybrid quantum-classical graph neural networks.

Subject Keywords

Quantum graph neural networks, Quantum machine learning, Particle track reconstruction

URI

https://hdl.handle.net/11511/94743

Journal

QUANTUM MACHINE INTELLIGENCE

DOI

https://doi.org/10.1007/s42484-021-00055-9

Collections

Department of Physics, Article

Suggestions

OpenMETU
Core

Quantum Graph Neural Networks for Track Reconstruction in Particle Physics and Beyond Tüysüz, Cenk; Demirköz, Melahat Bilge; Dobos, Daniel; Novotny, Kristiane; Potamianos, Karolos; Carminati, Federico; Vallecorsa, Sofia; Fracas, Fabio; Vlimant, Jeanroch (2020-10-22) The Large Hadron Collider (LHC) at the European Organisation for Nuclear Research (CERN) will undergo an upgrade to further increase the instantaneous rate of particle collisions (luminosity) and become the High Luminosity LHC. This increase in luminosity, will yield many more detector hits (occupancy), and thus measurements will pose a challenge to track reconstruction algorithms being responsible to determine particle trajectories from those hits. Similar challenges exist in non-high energy physics (HEP) ...
Performance of Particle Tracking Using a Quantum Graph Neural Network Tüysüz, Cenk; Novotny, Kristiane; Rieger, Carla; Carminati, Federico; Demirköz, Melahat Bilge; Dobos, Daniel; Fracas, Fabio; Potamianos, Karolos; Vallecorsa, Sofia; Vlimant, Jeanroch (null; 2020-12-02) The Large Hadron Collider (LHC) at the European Organisation for Nuclear Research (CERN) will be upgraded to further increase the instantaneous rate of particle collisions (luminosity) and become the High Luminosity LHC. This increase in luminosity, will yield many more detector hits (occupancy), and thus measurements will pose a challenge to track reconstruction algorithms being responsible to determine particle trajectories from those hits. This work explores the possibility of converting a novel Graph Ne...
Hybrid Quantum-Classical Graph Neural Networks for Particle Track Reconstruction at the Large Hadron Collider Tüysüz, Cenk; Demirköz, Melahat Bilge; Department of Physics (2021-8-5) Particle collider experiments aim to understand Nature at small scales. Particle accelerators, such as the Large Hadron Collider (LHC) at the European Organization for Nuclear Research (CERN), collide particles at high rates (MHz) and high energies (TeV) in order to probe such small scales. High collision rates may bring many computational challenges. One of these challenges is particle track reconstruction, which is the task of distinguishing the trajectories of charged particles passing through the detect...
Comparison of multi-cavity arrays for on-chip WDM applications Erdinç, Havva; Kocaman, Serdar; Department of Electrical and Electronics Engineering (2019) Researches about the interaction of single atoms with electromagnetic field create the foundation of cavity quantum electrodynamics (CQED) technology. Microlasers, photon bandgap structures and quantum dot structures in cavities are the initial examples of Cavity Quantum Electrodynamics. This thesis is focused on the comparison of multi-cavity arrays for on-chip wavelength division multiplexing (WDM) applications in the weak coupling regime. Firstly, single QD embedded cavity (cavity QD EIT) and cavity-cavi...
Quantum-resistant multivariate quadratic systems and digital signatures Altundağ, Esen; Cenk, Murat; Department of Cryptography (2019) In the light of technological advances, scientists expect that quantum computers will be generated and substitute with classical ones, then all symmetric and asymmetric (public-key) cryptosystems will be invalid in the near future. This causes the need for quantum-resistant algorithms all araund the world. That’s why, we have focused on multivariate public-key cryptosystems as a kind of post-quantum cryptography. In order to explain the root idea behind this kind of cryptosystems, as a starting point, the M...

Citation Formats

C. Tuysuz et al., “Hybrid quantum classical graph neural networks for particle track reconstruction,” QUANTUM MACHINE INTELLIGENCE, vol. 3, no. 2, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/94743.