Particle Transformer for Jet Tagging

TL;DR

This paper introduces JetClass, a large-scale dataset for jet tagging, and proposes Particle Transformer (ParT), a new model that leverages pairwise particle interactions to significantly improve jet classification performance.

Contribution

The paper presents JetClass, a large dataset for jet tagging, and introduces Particle Transformer, a novel architecture that outperforms previous models by incorporating pairwise particle interactions.

Findings

ParT surpasses ParticleNet in jet tagging accuracy.

Pre-trained ParT models improve performance on benchmark datasets.

JetClass dataset enables significant advancements in jet tagging research.

Abstract

Jet tagging is a critical yet challenging classification task in particle physics. While deep learning has transformed jet tagging and significantly improved performance, the lack of a large-scale public dataset impedes further enhancement. In this work, we present JetClass, a new comprehensive dataset for jet tagging. The JetClass dataset consists of 100 M jets, about two orders of magnitude larger than existing public datasets. A total of 10 types of jets are simulated, including several types unexplored for tagging so far. Based on the large dataset, we propose a new Transformer-based architecture for jet tagging, called Particle Transformer (ParT). By incorporating pairwise particle interactions in the attention mechanism, ParT achieves higher tagging performance than a plain Transformer and surpasses the previous state-of-the-art, ParticleNet, by a large margin. The pre-trained ParT models, once fine-tuned, also substantially enhance the performance on two widely adopted jet tagging benchmarks. The dataset, code and models are publicly available at https://github.com/jet-universe/particle_transformer.