GNN For Muon Particle Momentum estimation

Vishak K Bhat; Eric A. F. Reinhardt; Sergei Gleyzer

physics.data-anMar 3, 2026

GNN For Muon Particle Momentum estimation

Authors: Vishak K Bhat, Eric A. F. Reinhardt, Sergei Gleyzer

Organizations: IIT Dhanbad, India · Department of Physics and Astronomy, The University of Alabama, USA

Abstract

Due to a high rate of overall data generation relative to data generation of interest, the CMS experiment at the Large Hadron Collider uses a combination of hardware- and software-based triggers to select data for capture. Accurate momentum calculation is crucial for improving the efficiency of the CMS trigger systems, enabling better classification of low- and high- momentum particles and reducing false triggers. This paper explores the use of Graph Neural Networks (GNNs) for the momentum estimation task. We present two graph construction methods and apply a GNN model to leverage the inherent graph structure of the data. In this paper firstly, we show that the GNN outperforms traditional models like TabNet in terms of Mean Absolute Error (MAE), demonstrating its effectiveness in capturing complex dependencies within the data. Secondly we show that the dimension of the node feature is crucial for the efficiency of GNN.

Figures & tables

Model	MAE	Params	Inf. Speed	Epochs to
				Converge
TabNet	0.8855	7,488	0.0193 ms	20
GNN (4-dim node feat.)	0.8850	99,952	0.1391 ms	47
GNN (7-dim node feat.)	0.8474	101,152	0.114 ms	18

Table 1: Comparison of models on MAE, parameter count, inference speed, and convergence.

Model	MAE	MSE	Avg Inference Time (micro-sec)	No. of Parameters
TabNet	0.9607	2.9746	458.7	6696
GNN-bendAngle	1.202931	3.520059	522.204	5579
GNN-bendAngle2	1.215189	3.605358	530.19	5903
GNN-etaValue	1.146910	3.240220	522.204	5579
GNN-etaValue2	0.992087	2.525927	530.19	5903
GNN-etaValue3	1.145697	3.276628	614.565	6437

Table 2: Comparison of TabNet and GNN Models

Explore similar work

Characterization and upgrade of a quantum graph neural network for charged particle tracking
Mar 9, 2026Matteo Argenton, Laura Cappelli, Concezio BozziQuantum Neural Networks High-Energy Physics
Department of Physics and Earth Science, University of Ferrara, Via Saragat 1, Ferrara, 44122, Italy · INFN Ferrara, Via Saragat 1, Ferrara, 44122, Italy
Momentum-Conserving Graph Neural Networks for Deformable Objects
Apr 28, 2026Jiahong Wang, Logan Numerow, Stelian Coros +3Graph Neural Networks Physics-Informed ML
Max Planck Institute for Informatics · ETH Zurich · University of Bonn +1
Vision Transformers and Graph Neural Networks for Charged Particle Tracking in the ATLAS Muon Spectrometer
Mar 26, 2026Jonathan RenuschHigh-Energy Physics Graph Neural Networks
on behalf of the ATLAS Collaboration · CERN, Geneva, Switzerland

Mar 9, 2026J/K move · Enter open · S save

Characterization and upgrade of a quantum graph neural network for charged particle tracking

Matteo Argenton, Laura Cappelli, Concezio Bozzi

Department of Physics and Earth Science, University of Ferrara, Via Saragat 1, Ferrara, 44122, Italy · INFN Ferrara, Via Saragat 1, Ferrara, 44122, Italy

Quantum Neural Networks High-Energy Physics Hybrid Quantum-Classical ML

Open paper AskPDF arXiv

In the forthcoming years the LHC experiments are going to be upgraded to benefit from the substantial increase of the LHC instantaneous luminosity, which will lead to larger, denser events, and, consequently, greater complexity in reconstructing charged particle tracks, motivating frontier research in new technologies. Quantum machine learning models are being investigated as potential new approaches to high energy physics (HEP) tasks. We characterize and upgrade a quantum graph neural network (QGNN) architecture for charged particle track reconstruction on a simulated high luminosity dataset. The model operates on a set of event graphs, each built from the hits generated in tracking detector layers by particles produced in proton collisions, performing a classification of the possible hit connections between adjacent layers. In this approach the QGNN is designed as a hybrid architecture, interleaving classical feedforward networks with parametrized quantum circuits. We characterize the interplay between the classical and quantum components. We report on the principal upgrades to the original design, and present new evidence of improved training behavior, specifically in terms of convergence toward the final trained configuration.

Abstract

Explore similar work

Characterization and upgrade of a quantum graph neural network for charged particle tracking

Momentum-Conserving Graph Neural Networks for Deformable Objects

Vision Transformers and Graph Neural Networks for Charged Particle Tracking in the ATLAS Muon Spectrometer