Particle Transformer for Jet Tagging
This work addresses the problem of limited data for jet tagging in particle physics, offering a comprehensive dataset and improved model, though it is incremental in building on existing deep learning methods.
The authors tackled the lack of a large-scale public dataset for jet tagging in particle physics by introducing JetClass, a dataset with 100 M jets, and proposed Particle Transformer (ParT), a new Transformer-based architecture that surpasses the previous state-of-the-art, ParticleNet, by a large margin and enhances performance on benchmarks after fine-tuning.
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.