Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments

Abstract

A major task in particle physics is the measurement of rare signal processes. Even modest improvements in background rejection, at a fixed signal efficiency, can significantly enhance the measurement sensitivity. Building on prior research by others that incorporated physical symmetries into neural networks, this work extends those ideas to include additional physics-motivated features. Specifically, we introduce energy-dependent particle interaction strengths, derived from leading-order SM predictions, into modern deep learning architectures, including Transformer Architectures (Particle Transformer), and Graph Neural Networks (Particle Net). These interaction strengths, represented as the SM interaction matrix, are incorporated into the attention matrix (transformers) and edges (graphs). Our results in event classification show that the integration of all physics-motivated features improves background rejection by $10\%-40\%$ over baseline models, with an additional gain of up to $9\%$ due to the SM interaction matrix. This study also provides one of the broadest comparisons of event classifiers to date, demonstrating how various architectures perform across this task. A simplified statistical analysis demonstrates that these enhanced architectures yield significant improvements in signal significance compared to a graph network baseline.

Version 3 of this paper supersedes arXiv:2211.05143v2. 36 pages, 6 figures

References in corpus (17)

• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• An Introduction to PYTHIA 8.2
• Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS
• Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Lorentz Group Equivariant Neural Network for Particle Physics
• Observation of four-top-quark production in the multilepton final state with the ATLAS detector
• Point Cloud Transformers applied to Collider Physics
• Particle Transformer for Jet Tagging
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Observation of four top quark production in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Does Lorentz-symmetric design boost network performance in jet physics?
• Les Houches 2011: Physics at TeV Colliders New Physics Working Group Report
• Machine Learning Optimized Search for the $Z^{\prime }$ from $U(1{)}_{L_{\mu }-L_{\tau }}$ at the LHC

Cited by in corpus (1)

• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction