Particle Transformer for Jet Tagging

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.

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

Cited by in corpus (17)

• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• Enriching the physics program of the CMS experiment via data scouting and data parking
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
• Anomalies, Representations, and Self-Supervision
• A Lorentz-Equivariant Transformer for All of the LHC
• BIP: Boost Invariant Polynomials for Efficient Jet Tagging
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Heterogeneous Graph Neural Network for Identifying Hadronically Decayed Tau Leptons at the High Luminosity LHC
• Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments
• Fast Jet Tagging with MLP-Mixers on FPGAs
• MACK: Mismodeling Addressed with Contrastive Knowledge
• BitHEP -- The Limits of Low-Precision ML in HEP
• Reconstructing hadronically decaying tau leptons with a jet foundation model
• Large Language Models -- the Future of Fundamental Physics?
• jBOT: Semantic Jet Representation Clustering Emerges from Self-Distillation