mlsanityData to 14 Oct 2026

Detecting Symmetries with Neural Networks

arXiv 2003.13679 ↗First posted 30 Mar 2020physics.comp-ph cs.LG hep-thcited by 34

Not on the map. Why?

Abstract (arXiv)

Identifying symmetries in data sets is generally difficult, but knowledge about them is crucial for efficient data handling. Here we present a method how neural networks can be used to identify symmetries. We make extensive use of the structure in the embedding layer of the neural network which allows us to identify whether a symmetry is present and to identify orbits of the symmetry in the input. To determine which continuous or discrete symmetry group is present we analyse the invariant orbits in the input. We present examples based on rotation groups SO(n) and the unitary group SU(2). Further we find that this method is useful for the classification of complete intersection Calabi-Yau manifolds where it is crucial to identify discrete symmetries on the input space. For this example we present a novel data representation in terms of graphs.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 11; 2024: 5; 2025: 3; 2026: 4.

34 papers.

Sort:

  1. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 118
  2. 2023Generative Adversarial Symmetry Discoverycited by 42
  3. 2021Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlatorscited by 29
  4. 2021Machine-Learning Mathematical Structurescited by 25
  5. 2021Nonperturbative renormalization for the neural network-QFT correspondencecited by 24
  6. 2023Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras from First Principlescited by 22
  7. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  8. 2023Regularizing Towards Soft Equivariance Under Mixed Symmetriescited by 16
  9. 2021Machine Learning Calabi-Yau Hypersurfacescited by 15
  10. 2025Interpretable Machine Learning in Physics: A Reviewcited by 14
  11. 2021Symmetry meets AIcited by 13
  12. 2021Deep multi-task mining Calabi-Yau four-foldscited by 11
22 more
  1. 2022Cluster Algebras: Network Science and Machine Learningcited by 9
  2. 2023Discovering Sparse Representations of Lie Groups with Machine Learningcited by 8
  3. 2024Symmetry Discovery for Different Data Typescited by 8
  4. 2023Accelerated Discovery of Machine-Learned Symmetries: Deriving the Exceptional Lie Groups G2, F4 and E6cited by 6
  5. 2023Identifying the Group-Theoretic Structure of Machine-Learned Symmetriescited by 6
  6. 2023Oracle-Preserving Latent Flowscited by 5
  7. 2024A Triumvirate of AI Driven Theoretical Discoverycited by 5
  8. 2023Exploring how a Generative AI interprets musiccited by 4
  9. 2022Rotationally Equivariant Super-Resolution of Velocity Fields in Two-Dimensional Fluids Using Convolutional Neural Networkscited by 3
  10. 2023Non-parametric Hypothesis Tests for Distributional Group Symmetrycited by 3
  11. 2022From the String Landscape to the Mathematical Landscape: a Machine-Learning Outlookcited by 2
  12. 2025Learning finite symmetry groups of dynamical systems via equivariance detectioncited by 2
  13. 2022Machine-Learning the Classification of Spacetimescited by 1
  14. 2022Learning quantum symmetries with interactive quantum-classical variational algorithmscited by 1
  15. 2023Deep learning complete intersection Calabi-Yau manifoldscited by 1
  16. 2024Data-driven discovery of self-similarity using neural networkscited by 1
  17. 2024SymmetryLens: Unsupervised Symmetry Learning via Locality and Density Preservationcited by 1
  18. 2025Non-Gaussianities in Collider Metric Binningcited by 0
  19. 2026Global Symmetry and Orthogonal Transformations from Geometrical Moment n-tuplescited by 0
  20. 2026Discovering Symmetries in Neural Network Parameter Spacescited by 0
  21. 2026LieDiscover: Adaptive Symbolic Library Construction for Explicit Open-form Symmetry Discoverycited by 0
  22. 2026Symmetry Discovery in Quantum Learning: Observable-Level and Task-Level Inference from Finite Measurementscited by 0