A method to challenge symmetries in data with self-supervised learning

Abstract

Symmetries are key properties of physical models and of experimental designs, but any proposed symmetry may or may not be realized in nature. In this paper, we introduce a practical and general method to test such suspected symmetries in data, with minimal external input. Self-supervision, which derives learning objectives from data without external labelling, is used to train models to predict 'which is real?' between real data and symmetrically transformed alternatives. If these models make successful predictions in independent tests, then they challenge the targeted symmetries. Crucially, our method handles filtered data, which often arise from inefficiencies or deliberate selections, and which could give the illusion of asymmetry if mistreated. We use examples to demonstrate how the method works and how the models' predictions can be interpreted. Code and data are available at https://zenodo.org/record/6861702.

20 pages, 5 figures, reworked with more precise definitions

References in corpus (10)

• Bootstrap your own latent: A new approach to self-supervised Learning
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Lattice gauge equivariant convolutional neural networks
• SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention
• Symmetries, Safety, and Self-Supervision
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• SymmetryGAN: Symmetry Discovery with Deep Learning
• A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
• Chiral Measurements
• Hunting for vampires and other unlikely forms of parity violation at the Large Hadron Collider

Cited by in corpus (12)

• Calomplification -- The Power of Generative Calorimeter Models
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Anomaly Detection under Coordinate Transformations
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Anomalies, Representations, and Self-Supervision
• Non-resonant Anomaly Detection with Background Extrapolation
• Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders
• On the spatial distribution of the Large-Scale structure: An Unsupervised search for Parity Violation
• Hunting for vampires and other unlikely forms of parity violation at the Large Hadron Collider
• SymmetryLens: Unsupervised Symmetry Learning via Locality and Density Preservation