Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
166 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Quark/Gluon Discrimination and Top Tagging with Dual Attention Transformer (2307.04723v3)

Published 10 Jul 2023 in hep-ph

Abstract: Jet tagging is a crucial classification task in high energy physics. Recently the performance of jet tagging has been significantly improved by the application of deep learning techniques. In this study, we introduce a new architecture for jet tagging: the Particle Dual Attention Transformer (P-DAT). This novel transformer architecture stands out by concurrently capturing both global and local information, while maintaining computational efficiency. Regarding the self attention mechanism, we have extended the established attention mechanism between particles to encompass the attention mechanism between particle features. The particle attention module computes particle level interactions across all the particles, while the channel attention module computes attention scores between particle features, which naturally captures jet level interactions by taking all particles into account. These two kinds of attention mechanisms can complement each other. Further, we incorporate both the pairwise particle interactions and the pairwise jet feature interactions in the attention mechanism. We demonstrate the effectiveness of the P-DAT architecture in classic top tagging and quark-gluon discrimination tasks, achieving competitive performance compared to other benchmark strategies.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Identification of Jets Containing b𝑏bitalic_b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment. Technical report, CERN, Geneva, 2017. All figures including auxiliary figures are available at https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/ PUBNOTES/ATL-PHYS-PUB-2017-003.
  2. Quark versus Gluon Jet Tagging Using Jet Images with the ATLAS Detector. 7 2017.
  3. Probing stop pair production at the LHC with graph neural networks. JHEP, 08:055, 2019.
  4. Probing the triple Higgs boson coupling with machine learning at the LHC. Phys. Rev. D, 104(5):056003, 2021.
  5. Lisa Benato et al. Shared Data and Algorithms for Deep Learning in Fundamental Physics. Comput. Softw. Big Sci., 6(1):9, 2022.
  6. The anti-ktsubscript𝑘𝑡k_{t}italic_k start_POSTSUBSCRIPT italic_t end_POSTSUBSCRIPT jet clustering algorithm. JHEP, 04:063, 2008.
  7. Taoli Cheng. Recursive Neural Networks in Quark/Gluon Tagging. Comput. Softw. Big Sci., 2(1):3, 2018.
  8. Jet-Images: Computer Vision Inspired Techniques for Jet Tagging. JHEP, 02:118, 2015.
  9. DELPHES 3, A modular framework for fast simulation of a generic collider experiment. JHEP, 02:057, 2014.
  10. Rafael Teixeira de Lima. Sequence-based Machine Learning Models in Jet Physics. 2 2021.
  11. Jet-images — deep learning edition. JHEP, 07:069, 2016.
  12. Davit: Dual attention vision transformers. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXIV, pages 74–92. Springer, 2022.
  13. An image is worth 16x16 words: Transformers for image recognition at scale, 2021.
  14. Jet tagging in the Lund plane with graph networks. JHEP, 03:052, 2021.
  15. An efficient Lorentz equivariant graph neural network for jet tagging. JHEP, 07:030, 2022.
  16. PCT: Point cloud transformer. Computational Visual Media, 7(2):187–199, apr 2021.
  17. Xiangyang Ju et al. Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors. In 33rd Annual Conference on Neural Information Processing Systems, 3 2020.
  18. Deep-learning Top Taggers or The End of QCD? JHEP, 05:006, 2017.
  19. Energy Flow Networks: Deep Sets for Particle Jets. JHEP, 01:121, 2019.
  20. Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning. Phys. Rept., 841:1–63, 2020.
  21. Reconstructing boosted Higgs jets from event image segmentation. JHEP, 04:156, 2021.
  22. Boosting H→b⁢b¯→𝐻𝑏¯𝑏H\to b\bar{b}italic_H → italic_b over¯ start_ARG italic_b end_ARG with Machine Learning. JHEP, 10:101, 2018.
  23. Decoupled weight decay regularization, 2019.
  24. QCD-Aware Recursive Neural Networks for Jet Physics. JHEP, 01:057, 2019.
  25. A jet tagging algorithm of graph network with HaarPooling message passing. 10 2022.
  26. Pulling Out All the Tops with Computer Vision and Deep Learning. JHEP, 10:121, 2018.
  27. ABCNet: An attention-based method for particle tagging. Eur. Phys. J. Plus, 135(6):463, 2020.
  28. Point cloud transformers applied to collider physics. Mach. Learn. Sci. Tech., 2(3):035027, 2021.
  29. JEDI-net: a jet identification algorithm based on interaction networks. Eur. Phys. J. C, 80(1):58, 2020.
  30. ParticleNet: Jet Tagging via Particle Clouds. Phys. Rev. D, 101(5):056019, 2020.
  31. Particle Transformer for Jet Tagging. 2 2022.
  32. Detecting an axion-like particle with machine learning at the LHC. JHEP, 11:138, 2021.
  33. Graph Neural Networks in Particle Physics. 7 2020.
  34. An introduction to PYTHIA 8.2. Comput. Phys. Commun., 191:159–177, 2015.
  35. Attention is all you need, 2017.
  36. Dynamic graph CNN for learning on point clouds. CoRR, abs/1801.07829, 2018.
  37. Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5):1–12, 2019.
  38. Visual transformers: Token-based image representation and processing for computer vision, 2020.
Citations (10)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now