Hypergraph learning improves particle event reconstruction accuracy
Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion
Machine Learning
Summary
Reconstructing particle collisions means figuring out how particles created in high-energy experiments behaved before they disappeared. The authors break this task into two parts: matching detected particle signals to their original particles and guessing unseen neutrino behaviors. They introduce VyPER, which uses a special kind of network model called a hypergraph combined with a diffusion method to do both tasks together better than previous approaches. This improves understanding of events in proton collisions and helps with precise measurements in important physics areas.
What this means in practice
- •For particle physics experiment teams: Enhance reconstruction of particle collision events by integrating hypergraph learning to assign particle origins and predict invisible neutrino behavior accurately.
- •For medical imaging researchers: Adapt hypergraph and diffusion-based reconstruction methods from particle physics to improve complex image source assignment and signal inference in medical scans.
Authors
Lining Mao, Yvonne Peters, Ethan Simpson, Zihan Zhang
Abstract
In particle collider experiments, event reconstruction is the task of inferring the kinematics of short-lived particles produced in the hard scatter from the stable final states recorded by detectors. We decompose event reconstruction into two primary tasks: assigning measured jets and charged leptons to parent particles, and predicting unmeasured neutrino kinematics. We present VyPER, a novel geometric learning framework that represents collider events as hypergraphs with a physics-inspired topology. VyPER combines the supervised classification of hyperedges for particle assignment with a diffusion model for predicting neutrino kinematics, leveraging a joint loss function to optimize both reconstruction tasks within a unified framework. We showcase VyPER across several proton-proton collision processes, comparing its performance to existing analytical and machine-learning-based reconstruction techniques. In doing so, we demonstrate that accurate event reconstruction is achievable across a diverse range of Standard Model physics processes, opening new avenues for precision measurements in the Higgs boson, electroweak, and top-quark sectors.