An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging

TL;DR

LorentzNet is a novel, efficient deep learning model that preserves Lorentz symmetry for jet tagging in particle physics, achieving superior performance and better generalization with less training data.

Contribution

Introduces LorentzNet, a computationally efficient Lorentz-equivariant graph neural network for jet tagging, improving accuracy and generalization over existing methods.

Findings

Achieves state-of-the-art jet tagging performance.

Significantly outperforms existing algorithms.

Requires fewer training samples for high accuracy.

Abstract

Deep learning methods have been increasingly adopted to study jets in particle physics. Since symmetry-preserving behavior has been shown to be an important factor for improving the performance of deep learning in many applications, Lorentz group equivariance - a fundamental spacetime symmetry for elementary particles - has recently been incorporated into a deep learning model for jet tagging. However, the design is computationally costly due to the analytic construction of high-order tensors. In this article, we introduce LorentzNet, a new symmetry-preserving deep learning model for jet tagging. The message passing of LorentzNet relies on an efficient Minkowski dot product attention. Experiments on two representative jet tagging benchmarks show that LorentzNet achieves the best tagging performance and improves significantly over existing state-of-the-art algorithms. The preservation of Lorentz symmetry also greatly improves the efficiency and generalization power of the model, allowing LorentzNet to reach highly competitive performance when trained on only a few thousand jets. Code and models are available at \url{https://github.com/sdogsq/LorentzNet-release}.