Reconstructing particles in jets using set transformer and hypergraph prediction networks.
Saved in:
| Title: | Reconstructing particles in jets using set transformer and hypergraph prediction networks. |
|---|---|
| Authors: | Di Bello, Francesco Armando1 (AUTHOR), Dreyer, Etienne2 (AUTHOR), Ganguly, Sanmay3 (AUTHOR), Gross, Eilam2 (AUTHOR), Heinrich, Lukas4 (AUTHOR), Ivina, Anna2 (AUTHOR), Kado, Marumi5,6 (AUTHOR), Kakati, Nilotpal2 (AUTHOR) nilotpal.kakati@weizmann.ac.il, Santi, Lorenzo6 (AUTHOR), Shlomi, Jonathan2 (AUTHOR), Tusoni, Matteo6 (AUTHOR) |
| Source: | European Physical Journal C -- Particles & Fields. Jul2023, Vol. 83 Issue 7, p1-18. 18p. |
| Subjects: | Collisions (Nuclear physics), Hyperfragments, Detectors, Feynman diagrams |
| 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. [ABSTRACT FROM AUTHOR] |
| Copyright of European Physical Journal C -- Particles & Fields is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| 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. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 14346044 |
| DOI: | 10.1140/epjc/s10052-023-11677-7 |
