Reconstructing particles in jets using set transformer and hypergraph prediction networks
Abstract
The task of reconstructing particles from low-level detector response data to predict the set of final state particles in collision events represents a set-to-set prediction task requiring the use of multiple features and their correlations in the input data. We deploy three separate set-to-set neural network architectures to reconstruct particles in events containing a single jet in a fully-simulated calorimeter. Performance is evaluated in terms of particle reconstruction quality, properties regression, and jet-level metrics. The results demonstrate that such a high dimensional end-to-end approach succeeds in surpassing basic parametric approaches in disentangling individual neutral particles inside of jets and optimizing the use of complementary detector information. In particular, the performance comparison favors a novel architecture based on learning hypergraph structure, HGPflow, which benefits from a physically-interpretable approach to particle reconstruction.
Cite
@article{arxiv.2212.01328,
title = {Reconstructing particles in jets using set transformer and hypergraph prediction networks},
author = {Francesco Armando Di Bello and Etienne Dreyer and Sanmay Ganguly and Eilam Gross and Lukas Heinrich and Anna Ivina and Marumi Kado and Nilotpal Kakati and Lorenzo Santi and Jonathan Shlomi and Matteo Tusoni},
journal= {arXiv preprint arXiv:2212.01328},
year = {2023}
}
Comments
17 pages, 21 figures