Home > Research > Publications & Outputs > Hybrid quantum classical graph neural networks ...

Links

Text available via DOI:

View graph of relations

Hybrid quantum classical graph neural networks for particle track reconstruction

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Hybrid quantum classical graph neural networks for particle track reconstruction. / Tüysüz, C.; Rieger, C.; Novotny, K.; Demirköz, B.; Dobos, D.; Potamianos, K.; Vallecorsa, S.; Vlimant, J.-R.; Forster, R.

In: Quantum Machine Intelligence, Vol. 3, No. 2, 29, 28.11.2021.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Tüysüz, C, Rieger, C, Novotny, K, Demirköz, B, Dobos, D, Potamianos, K, Vallecorsa, S, Vlimant, J-R & Forster, R 2021, 'Hybrid quantum classical graph neural networks for particle track reconstruction', Quantum Machine Intelligence, vol. 3, no. 2, 29. https://doi.org/10.1007/s42484-021-00055-9

APA

Tüysüz, C., Rieger, C., Novotny, K., Demirköz, B., Dobos, D., Potamianos, K., Vallecorsa, S., Vlimant, J-R., & Forster, R. (2021). Hybrid quantum classical graph neural networks for particle track reconstruction. Quantum Machine Intelligence, 3(2), [29]. https://doi.org/10.1007/s42484-021-00055-9

Vancouver

Tüysüz C, Rieger C, Novotny K, Demirköz B, Dobos D, Potamianos K et al. Hybrid quantum classical graph neural networks for particle track reconstruction. Quantum Machine Intelligence. 2021 Nov 28;3(2). 29. https://doi.org/10.1007/s42484-021-00055-9

Author

Tüysüz, C. ; Rieger, C. ; Novotny, K. ; Demirköz, B. ; Dobos, D. ; Potamianos, K. ; Vallecorsa, S. ; Vlimant, J.-R. ; Forster, R. / Hybrid quantum classical graph neural networks for particle track reconstruction. In: Quantum Machine Intelligence. 2021 ; Vol. 3, No. 2.

Bibtex

@article{0e89632354c244b69f95fe1448149018,
title = "Hybrid quantum classical graph neural networks for particle track reconstruction",
abstract = "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. ",
keywords = "Particle track reconstruction, Quantum graph neural networks, Quantum machine learning, Colliding beam accelerators, Graph neural networks, High energy physics, Machine learning, Multilayer neural networks, Large Hadron Collider, Large-hadron colliders, Particle tracks, Quantum graph, Quantum graph neural network, Quantum-classical, Track reconstruction, Luminance",
author = "C. T{\"u}ys{\"u}z and C. Rieger and K. Novotny and B. Demirk{\"o}z and D. Dobos and K. Potamianos and S. Vallecorsa and J.-R. Vlimant and R. Forster",
year = "2021",
month = nov,
day = "28",
doi = "10.1007/s42484-021-00055-9",
language = "English",
volume = "3",
journal = "Quantum Machine Intelligence",
issn = "2524-4906",
publisher = "Springer",
number = "2",

}

RIS

TY - JOUR

T1 - Hybrid quantum classical graph neural networks for particle track reconstruction

AU - Tüysüz, C.

AU - Rieger, C.

AU - Novotny, K.

AU - Demirköz, B.

AU - Dobos, D.

AU - Potamianos, K.

AU - Vallecorsa, S.

AU - Vlimant, J.-R.

AU - Forster, R.

PY - 2021/11/28

Y1 - 2021/11/28

N2 - 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.

AB - 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.

KW - Particle track reconstruction

KW - Quantum graph neural networks

KW - Quantum machine learning

KW - Colliding beam accelerators

KW - Graph neural networks

KW - High energy physics

KW - Machine learning

KW - Multilayer neural networks

KW - Large Hadron Collider

KW - Large-hadron colliders

KW - Particle tracks

KW - Quantum graph

KW - Quantum graph neural network

KW - Quantum-classical

KW - Track reconstruction

KW - Luminance

U2 - 10.1007/s42484-021-00055-9

DO - 10.1007/s42484-021-00055-9

M3 - Journal article

VL - 3

JO - Quantum Machine Intelligence

JF - Quantum Machine Intelligence

SN - 2524-4906

IS - 2

M1 - 29

ER -