mlsanityData to 14 Oct 2026

PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics

arXiv 2211.00454 ↗First posted 1 Nov 2022hep-ph cs.LG hep-excited by 26

Not on the map. Why?

Abstract (arXiv)

Many current approaches to machine learning in particle physics use generic architectures that require large numbers of parameters and disregard underlying physics principles, limiting their applicability as scientific modeling tools. In this work, we present a machine learning architecture that uses a set of inputs maximally reduced with respect to the full 6-dimensional Lorentz symmetry, and is fully permutation-equivariant throughout. We study the application of this network architecture to the standard task of top quark tagging and show that the resulting network outperforms all existing competitors despite much lower model complexity. In addition, we present a Lorentz-covariant variant of the same network applied to a 4-momentum regression task.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 11 of its 35 references that are in the map. First posted on arXiv 1 Nov 2022.

Builds on

11 of 35 references.

References · 11

  1. 2017Deep Setscited by 1,421
  2. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  3. 2021Scalars are universal: Equivariant machine learning, structured like classical physicscited by 127
  4. 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 121
  5. 2019On the Limitations of Representing Functions on Setscited by 90
  6. 2018Energy Flow Networks: Deep Sets for Particle Jetscited by 84
  7. 2020Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectorscited by 80
  8. 2021Only Train Once: A One-Shot Neural Network Training And Pruning Frameworkcited by 70
  9. 2020Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physicscited by 34
  10. 2022Exponential Separations in Symmetric Neural Networkscited by 10
  11. 2021Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physicscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 7; 2025: 5; 2026: 5.

26 papers.

Sort:

By area:

  1. 2024Does equivariance matter at scale?cited by 52
  2. 2024Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physicscited by 38
  3. 2024A Lorentz-Equivariant Transformer for All of the LHCcited by 28
  4. 2024Clifford-Steerable Convolutional Neural Networkscited by 25
  5. 2024Ultrafast jet classification on FPGAs for the HL-LHCcited by 12
  6. 2025Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariantcited by 12
  7. 2023Anomalies, Representations, and Self-Supervisioncited by 11
  8. 2023Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networkscited by 7
  9. 2023Equivariance Is Not All You Need: Characterizing the Utility of Equivariant Graph Neural Networks for Particle Physics Taskscited by 5
  10. 2023mathbbZ2× mathbbZ2 Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networkscited by 4
  11. 2025Equivariant Neural Networks for General Linear Symmetries on Lie Algebrascited by 4
  12. 2022Feature Selection with Distance Correlationcited by 3
14 more
  1. 2023PCN: A Deep Learning Approach to Jet Tagging Utilizing Novel Graph Construction Methods and Chebyshev Graph Convolutionscited by 3
  2. 2023Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Cloudscited by 2
  3. 2026Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Taskscited by 2
  4. 2024Image and Point-cloud Classification for Jet Analysis in High-Energy Physics: A surveycited by 1
  5. 2025Learning symmetries in datasetscited by 1
  6. 2025Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformercited by 1
  7. 2025KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Taggingcited by 1
  8. 2026How unconstrained machine-learning models learn physical symmetriescited by 1
  9. 2026Unknown Unknowns: Model Misspecification in Machine Learning for Physicscited by 1
  10. 2023A Geometric Insight into Equivariant Message Passing Neural Networks on Riemannian Manifoldscited by 0
  11. 202319 Parameters Is All You Need: Tiny Neural Networks for Particle Physicscited by 0
  12. 2024Moments of Clarity: Streamlining Latent Spaces in Machine Learning using Moment Poolingcited by 0
  13. 2026Generative models on phase spacecited by 0
  14. 2026Predict before you train: Scaling Laws for particle physics foundation modelscited by 0