Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction

Quantum Machine Intelligence manuscript No. (will be inserted by the editor) Abstract The Large Hadron Collider (LHC) at the Keywords Quantum Graph Neural Networks Quantum European Organisation for Nuclear Research (CERN) Machine Learning Particle Track Reconstruction 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 1 Introduction will significantly increase the number of particles interacting with the detector. The interaction of Particle accelerator experiments aim to understand the particles with a detector is referred to as "hit". The nature of particles by colliding groups of particles at HL-LHC will yield many more detector hits, which will high energies and try to observe creation of particles pose a combinatorial challenge by using reconstruction and their decays, e.g. to validate theories. The Large algorithms to determine particle trajectories from those Hadron Collider (LHC) at the European Organisation hits. This work explores the possibility of converting for Nuclear Research (CERN) provides proton-proton a novel Graph Neural Network model, that can optimally collisions to four main experiments as well as other take into account the sparse nature of the tracking small experiments and fixed-target experiments. In order detector data and their complex geometry, to a Hybrid to achieve a high sensitivity, these experiments use Quantum-Classical Graph Neural Network that advanced software and hardware.