mlsanityData to 7 Oct 2026

Particle Transformer for Jet Tagging

arXiv 2202.03772 ↗First posted 8 Feb 2022hep-ph cs.LG hep-excited by 95

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Builds on 26 of its 68 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

26 of 68 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  9. 2020Reformer: The Efficient Transformercited by 1,658
  10. 2017Deep Setscited by 1,394
  11. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  12. 2021Going deeper with Image Transformerscited by 759
14 more
  1. 2020PCT: Point cloud transformercited by 730
  2. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
  3. 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 120
  4. 2018Energy Flow Networks: Deep Sets for Particle Jetscited by 83
  5. 2021NormFormer: Improved Transformer Pretraining with Extra Normalizationcited by 83
  6. 2019ParticleNet: Jet Tagging via Particle Cloudscited by 64
  7. 2021Particle Cloud Generation with Message Passing Generative Adversarial Networkscited by 45
  8. 2015Jet-Images -- Deep Learning Editioncited by 41
  9. 2021Point Cloud Transformers applied to Collider Physicscited by 23
  10. 2017QCD-Aware Recursive Neural Networks for Jet Physicscited by 22
  11. 2020Jet tagging in the Lund plane with graph networkscited by 22
  12. 2019GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloudcited by 15
  13. 2021A FAIR and AI-ready Higgs boson decay datasetcited by 14
  14. 2021Particle Convolution for High Energy Physicscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 21; 2024: 20; 2025: 27; 2026: 23.

95 papers.

Sort:

By area:

  1. 2024OmniJet-α: The first cross-task foundation model for particle physicscited by 41
  2. 2024Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physicscited by 36
  3. 2023PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physicscited by 27
  4. 2024A Lorentz-Equivariant Transformer for All of the LHCcited by 27
  5. 2023Explainable Equivariant Neural Networks for Particle Physics: PELICANcited by 22
  6. 2024Is Tokenization Needed for Masked Particle Modelling?cited by 20
  7. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  8. 2024Finetuning Foundation Models for Joint Analysis Optimizationcited by 18
  9. 2023A General Framework for Equivariant Neural Networks on Reductive Lie Groupscited by 16
  10. 2025OmniJet-αC: Learning point cloud calorimeter simulations using generative transformerscited by 14
  11. 2024Ultrafast jet classification on FPGAs for the HL-LHCcited by 12
  12. 2024Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physicscited by 12
38 more
  1. 2026Neural Scaling Laws for Boosted Jet Taggingcited by 11
  2. 2023Anomalies, Representations, and Self-Supervisioncited by 10
  3. 2024A Language Model for Particle Trackingcited by 10
  4. 2025Foundation models for high-energy physicscited by 10
  5. 2025Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliderscited by 8
  6. 2022BIP: Boost Invariant Polynomials for Efficient Jet Taggingcited by 7
  7. 2023Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networkscited by 7
  8. 2023Flow Matching Beyond Kinematics: Generating Jets with Particle-ID and Trajectory Displacement Informationcited by 7
  9. 2022A Detailed Study of Interpretability of Deep Neural Network based Top Taggerscited by 6
  10. 2023Fast Particle-based Anomaly Detection Algorithm with Variational Autoencodercited by 6
  11. 2024Ultra Fast Transformers on FPGAs for Particle Physics Experimentscited by 6
  12. 2025RINO: Renormalization Group Invariance with No Labelscited by 6
  13. 2025Sub-microsecond Transformers for Jet Tagging on FPGAscited by 6
  14. 2022Leveraging universality of jet taggers through transfer learningcited by 5
  15. 2023Equivariance Is Not All You Need: Characterizing the Utility of Equivariant Graph Neural Networks for Particle Physics Taskscited by 5
  16. 2024Optimal Equivariant Architectures from the Symmetries of Matrix-Element Likelihoodscited by 5
  17. 2024TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Eracited by 4
  18. 2025Equivariant Neural Networks for General Linear Symmetries on Lie Algebrascited by 4
  19. 2022Learning Tree Structures from Leaves For Particle Decay Reconstructioncited by 3
  20. 2023PCN: A Deep Learning Approach to Jet Tagging Utilizing Novel Graph Construction Methods and Chebyshev Graph Convolutionscited by 3
  21. 2023Differentiable Vertex Fitting for Jet Flavour Taggingcited by 3
  22. 2023Learning to Optimise Wind Farms with Graph Transformerscited by 3
  23. 2023Efficient and Robust Jet Tagging at the LHC with Knowledge Distillationcited by 3
  24. 2025Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physicscited by 3
  25. 2025Spatially Aware Linear Transformer (SAL-T) for Particle Jet Taggingcited by 3
  26. 2025Enhancing next token prediction based pre-training for jet foundation modelscited by 3
  27. 2026JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggerscited by 3
  28. 2023Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surfacecited by 2
  29. 2023Graph Structure from Point Clouds: Geometric Attention is All You Needcited by 2
  30. 2023AdamMCMC: Combining Metropolis Adjusted Langevin with Momentum-based Optimizationcited by 2
  31. 2024MACK: Mismodeling Addressed with Contrastive Knowledgecited by 2
  32. 2025The Pareto Frontier of Resilient Jet Taggingcited by 2
  33. 2025Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extractioncited by 2
  34. 2025AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testingcited by 2
  35. 2026Towards Tensor Network Models for Low-Latency Jet Tagging on FPGAscited by 2
  36. 2026The Radio-Frequency Transformer for Signal Separationcited by 2
  37. 2026JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physicscited by 2
  38. 2023JetLOV: Enhancing Jet Tree Tagging through Neural Network Learning of Optimal LundNet Variablescited by 1

50 most cited of 95 All 95 (JSON)