Reconstructing short-lived particles using hypergraph representation learning
hep-ph, cs.LG, hep-ex
Submitted: 2024-02-15
Updated: 2025-02-12
Comments: 13 pages, 10 figures. Published by Physical Review D (PRD)
DOI: 10.1103/PhysRevD.111.032004
Code: https://github.com/tzuhanchang/HyPER
License: http://creativecommons.org/licenses/by/4.0/
The gist: In collider experiments, the kinematic reconstruction of heavy, short-lived particles is vital for precision tests of the Standard Model and in searches for physics beyond it.
Terminology
Abstract
In collider experiments, the kinematic reconstruction of heavy, short-lived particles is vital for precision tests of the Standard Model and in searches for physics beyond it. Performing kinematic reconstruction in collider events with many final-state jets, such as the all-hadronic decay of top-antitop quark pairs, is challenging. We present HyPER: Hypergraph for Particle Event Reconstruction, a novel architecture based on graph neural networks that uses hypergraph representation learning to build more powerful and efficient representations of collider events. HyPER is used to reconstruct parent particles from sets of final-state objects. Trained and tested on simulation, the HyPER model is shown to perform favorably when compared to existing state-of-the-art reconstruction techniques, while demonstrating superior parameter efficiency. The novel hypergraph approach allows the method to be applied to particle reconstruction in a multitude of different physics processes.
Sources
- Deep Hypergraph Structure Learning
- How Attentive are Graph Attention Networks?
- Deep Learning using Rectified Linear Units (ReLU)
- Understanding deep learning requires rethinking generalization
- Neural Message Passing for Quantum Chemistry
- Relational inductive biases, deep learning, and graph networks
- Relational inductive bias for physical construction in humans and machines
- Graph networks as learnable physics engines for inference and control
- Improving neural networks by preventing co-adaptation of feature detectors
Related papers
- Classification of g-modes for neutron stars with a strong transition: Novel universal relation including slow stable hybrid stars
- Higgsino Dark Matter Interpretation of the LUX-ZEPLIN 248 keV Nuclear-Recoil Event
- A Unified Bogoliubov Approach to Primordial Gravitational Waves: From Inflation to Reheating
- Probing Memory-Burdened Primordial Black Holes with High-Energy Neutrinos
- Enhanced Dark Matter Quantum Sensing via Phase-Space Geometric Interferometry
- Axions as Dark Matter, Dark Energy, and Dark Radiation