mlsanityData to 7 Oct 2026

KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics example

arXiv 2408.02743 ↗First posted 5 Aug 2024hep-ph cs.LG hep-excited by 4

Not on the map. Why?

Abstract (arXiv)

Recently, Kolmogorov-Arnold Networks (KANs) have been proposed as an alternative to multilayer perceptrons, suggesting advantages in performance and interpretability. We study a typical binary event classification task in high-energy physics including high-level features and comment on the performance and interpretability of KANs in this context. Consistent with expectations, we find that the learned activation functions of a one-layer KAN resemble the univariate log-likelihood ratios of the respective input features. In deeper KANs, the activations in the first layer differ from those in the one-layer KAN, which indicates that the deeper KANs learn more complex representations of the data, a pattern commonly observed in other deep-learning architectures. We study KANs with different depths and widths and we compare them to multilayer perceptrons in terms of performance and number of trainable parameters. For the chosen classification task, we do not find that KANs are more parameter efficient. However, small KANs may offer advantages in terms of interpretability that come at the cost of only a moderate loss in performance.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 52 of its 102 references that are in the map. First posted on arXiv 5 Aug 2024.

Builds on

52 of 102 references.

References · 52

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  6. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  8. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  9. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generationcited by 176
  10. 2024Kolmogorov-Arnold Networks are Radial Basis Function Networkscited by 125
  11. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 118
  12. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
38 more
  1. 2024A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networkscited by 103
  2. 2020Neural Networks Fail to Learn Periodic Functions and How to Fix Itcited by 97
  3. 2024Kolmogorov-Arnold Networks (KANs) for Time Series Analysiscited by 97
  4. 2024DeepOKAN: Deep Operator Network Based on Kolmogorov Arnold Networks for Mechanics Problemscited by 82
  5. 2021A Living Review of Machine Learning for Particle Physicscited by 77
  6. 2024Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretabilitycited by 69
  7. 2014Learning Activation Functions to Improve Deep Neural Networkscited by 62
  8. 2024fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functionscited by 60
  9. 2021Machine Learning in the Search for New Fundamental Physicscited by 50
  10. 2024A Temporal Kolmogorov-Arnold Transformer for Time Series Forecastingcited by 50
  11. 2019Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theoremcited by 49
  12. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 48
  13. 2024Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensingcited by 46
  14. 2024BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold Networkscited by 43
  15. 2024Demonstrating the Efficacy of Kolmogorov-Arnold Networks in Vision Taskscited by 39
  16. 2024Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networkscited by 37
  17. 2024Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problemscited by 35
  18. 2019Learning Activation Functions: A new paradigm for understanding Neural Networkscited by 33
  19. 2022ExSpliNet: An interpretable and expressive spline-based neural networkcited by 33
  20. 2024Unveiling the Power of Wavelets: A Wavelet-based Kolmogorov-Arnold Network for Hyperspectral Image Classificationcited by 33
  21. 2024Suitability of KANs for Computer Vision: A preliminary investigationcited by 33
  22. 2024GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networkscited by 31
  23. 2024A Benchmarking Study of Kolmogorov-Arnold Networks on Tabular Datacited by 25
  24. 2024Predictive Modeling of Flexible EHD Pumps using Kolmogorov-Arnold Networkscited by 23
  25. 2024Smooth Kolmogorov Arnold networks enabling structural knowledge representationcited by 22
  26. 2024Exploring the Limitations of Kolmogorov-Arnold Networks in Classification: Insights to Software Training and Hardware Implementationcited by 22
  27. 2022Neural Network Architecture Beyond Width and Depthcited by 17
  28. 2024Reduced Effectiveness of Kolmogorov-Arnold Networks on Functions with Noisecited by 17
  29. 2024Inferring turbulent velocity and temperature fields and their statistics from Lagrangian velocity measurements using physics-informed Kolmogorov-Arnold Networkscited by 15
  30. 2024DropKAN: Regularizing KANs by masking post-activationscited by 14
  31. 2023On the Optimal Expressive Power of ReLU DNNs and Its Application in Approximation with Kolmogorov Superposition Theoremcited by 13
  32. 2024Endowing Interpretability for Neural Cognitive Diagnosis by Efficient Kolmogorov-Arnold Networkscited by 12
  33. 2024SCKansformer: Fine-Grained Classification of Bone Marrow Cells via Kansformer Backbone and Hierarchical Attention Mechanismscited by 10
  34. 2024Leveraging KANs For Enhanced Deep Koopman Operator Discoverycited by 9
  35. 2024COEFF-KANs: A Paradigm to Address the Electrolyte Field with KANscited by 9
  36. 2024DKL-KAN: Scalable Deep Kernel Learning using Kolmogorov-Arnold Networkscited by 7
  37. 2024Deep State Space Recurrent Neural Networks for Time Series Forecastingcited by 6
  38. 2024HyperKAN: Kolmogorov-Arnold Networks make Hyperspectral Image Classificators Smartercited by 5

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Explainable fault and severity classification for rolling element bearings using Kolmogorov-Arnold networkscited by 2
  2. 2026Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networkscited by 1
  3. 2025TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentationcited by 0
  4. 2026Functional anatomy of Pythia-Herwig differences with Kolmogorov-Arnold networkscited by 0