EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Calafiura, Paolo, Chan, Jay, Delabrouille, Loic, Wang, Brandon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910535002357760
author Calafiura, Paolo
Chan, Jay
Delabrouille, Loic
Wang, Brandon
author_facet Calafiura, Paolo
Chan, Jay
Delabrouille, Loic
Wang, Brandon
contents Track reconstruction is a crucial task in particle experiments and is traditionally very computationally expensive due to its combinatorial nature. Recently, graph neural networks (GNNs) have emerged as a promising approach that can improve scalability. Most of these GNN-based methods, including the edge classification (EC) and the object condensation (OC) approach, require an input graph that needs to be constructed beforehand. In this work, we consider a one-shot OC approach that reconstructs particle tracks directly from a set of hits (point cloud) by recursively applying graph attention networks with an evolving graph structure. This approach iteratively updates the graphs and can better facilitate the message passing across each graph. Preliminary studies on the TrackML dataset show better track performance compared to the methods that require a fixed input graph.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13925
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstruction
Calafiura, Paolo
Chan, Jay
Delabrouille, Loic
Wang, Brandon
Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Phenomenology
Track reconstruction is a crucial task in particle experiments and is traditionally very computationally expensive due to its combinatorial nature. Recently, graph neural networks (GNNs) have emerged as a promising approach that can improve scalability. Most of these GNN-based methods, including the edge classification (EC) and the object condensation (OC) approach, require an input graph that needs to be constructed beforehand. In this work, we consider a one-shot OC approach that reconstructs particle tracks directly from a set of hits (point cloud) by recursively applying graph attention networks with an evolving graph structure. This approach iteratively updates the graphs and can better facilitate the message passing across each graph. Preliminary studies on the TrackML dataset show better track performance compared to the methods that require a fixed input graph.
title EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstruction
topic Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2407.13925