SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention

Abstract

The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics. Collisions typically produce variable-size sets of observed particles which have inherent ambiguities complicating the assignment of observed particles to the decay products of the heavy particles. Current strategies for tackling these challenges in the physics community ignore the physical symmetries of the decay products and consider all possible assignment permutations and do not scale to complex configurations. Attention based deep learning methods for sequence modelling have achieved state-of-the-art performance in natural language processing, but they lack built-in mechanisms to deal with the unique symmetries found in physical set-assignment problems. We introduce a novel method for constructing symmetry-preserving attention networks which reflect the problem's natural invariances to efficiently find assignments without evaluating all permutations. This general approach is applicable to arbitrarily complex configurations and significantly outperforms current methods, improving reconstruction efficiency between 19\% - 35\% on typical benchmark problems while decreasing inference time by two to five orders of magnitude on the most complex events, making many important and previously intractable cases tractable. A full code repository containing a general library, the specific configuration used, and a complete dataset release, are avaiable at https://github.com/Alexanders101/SPANet

published in SciPost

References in corpus (2)

• 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

Cited by in corpus (26)

• Symmetries, Safety, and Self-Supervision
• ν-Flows: Conditional Neutrino Regression
• Quantum Information meets High-Energy Physics: Input to the update of the European Strategy for Particle Physics
• A method to challenge symmetries in data with self-supervised learning
• Deducing Neutron Star Equation of State Parameters Directly From Telescope Spectra with Uncertainty-Aware Machine Learning
• HHH Whitepaper
• Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
• ${\nu }^2$-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows
• A Holistic Approach to Predicting Top Quark Kinematic Properties with the Covariant Particle Transformer
• Resolving Extreme Jet Substructure
• Portraying Double Higgs at the Large Hadron Collider II
• Inclusive and differential cross-section measurements of $t\bar{t}Z$ production in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector, including EFT and spin-correlation interpretations
• Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks
• Boosted top tagging and its interpretation using Shapley values
• Parton Labeling without Matching: Unveiling Emergent Labelling Capabilities in Regression Models
• Semi-supervised permutation invariant particle-level anomaly detection
• A search for R-parity-violating supersymmetry in final states containing many jets in $pp$ collisions at $\sqrt{s}=13\text{TeV}$ with the ATLAS detector
• Reconstructing short-lived particles using hypergraph representation learning
• PAIReD jet: A multi-pronged resonance tagging strategy across all Lorentz boosts
• Reconstruction of boosted and resolved multi-Higgs-boson events with symmetry-preserving attention networks
• Determination of the initial condition for the Balitsky-Kovchegov equation with transformers
• Quantum-annealing-inspired algorithms for multijet clustering
• Jet Rotational Metrics
• Solving Combinatorial Problems at Particle Colliders Using Machine Learning
• Tagging ultra-boosted jets at FCC-hh using machine learning techniques
• TIGER: A Topology-Agnostic, Hierarchical Graph Network for Event Reconstruction