تقرير
Particle Transformer for Jet Tagging
| العنوان: | Particle Transformer for Jet Tagging |
|---|---|
| المؤلفون: | Qu, Huilin, Li, Congqiao, Qian, Sitian |
| المصدر: | Proceedings of the 39th International Conference on Machine Learning, PMLR 162:18281-18292, 2022 |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science High Energy Physics - Experiment High Energy Physics - Phenomenology Physics (Other) |
| مصطلحات موضوعية: | High Energy Physics - Phenomenology, Computer Science - Machine Learning, High Energy Physics - Experiment, Physics - Data Analysis, Statistics and Probability |
| الوصف: | 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. Comment: 12 pages, 3 figures. Accepted to the 39th International Conference on Machine Learning (ICML), 2022. v3: fixed a typo on the interaction matrix dimensionality in Sec. 4 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2202.03772 |
| رقم الأكسشن: | edsarx.2202.03772 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |