mlsanityData to 7 Oct 2026

A Benchmarking Study of Kolmogorov-Arnold Networks on Tabular Data

arXiv 2406.14529 ↗First posted 20 Jun 2024cs.LG cs.AIcited by 25

Not on the map. Why?

Abstract (arXiv)

Kolmogorov-Arnold Networks (KANs) have very recently been introduced into the world of machine learning, quickly capturing the attention of the entire community. However, KANs have mostly been tested for approximating complex functions or processing synthetic data, while a test on real-world tabular datasets is currently lacking. In this paper, we present a benchmarking study comparing KANs and Multi-Layer Perceptrons (MLPs) on tabular datasets. The study evaluates task performance and training times. From the results obtained on the various datasets, KANs demonstrate superior or comparable accuracy and F1 scores, excelling particularly in datasets with numerous instances, suggesting robust handling of complex data. We also highlight that this performance improvement of KANs comes with a higher computational cost when compared to MLPs of comparable sizes.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 4 of its 25 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

4 of 25 references.

References · 4

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  3. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  4. 2022Neural Basis Models for Interpretabilitycited by 56

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 12; 2026: 3.

25 papers.

Sort:

By area:

  1. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 116
  2. 2024A Survey on Kolmogorov-Arnold Networkcited by 67
  3. 2024Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networkscited by 11
  4. 2025Initialization Schemes for Kolmogorov-Arnold Networks: An Empirical Studycited by 10
  5. 2024Multifidelity Kolmogorov-Arnold Networkscited by 9
  6. 2024Rethinking the Function of Neurons in KANscited by 5
  7. 2024Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptronscited by 5
  8. 2025CVKAN: Complex-Valued Kolmogorov-Arnold Networkscited by 5
  9. 2024KAN we improve on HEP classification tasks? Kolmogorov-Arnold Networks applied to an LHC physics examplecited by 4
  10. 2024TabKANet: Tabular Data Modeling with Kolmogorov-Arnold Network and Transformercited by 4
  11. 2024KAN v.s. MLP for Offline Reinforcement Learningcited by 3
  12. 2025Physics-informed KAN PointNet: Deep learning for simultaneous solutions to inverse problems in incompressible flow on numerous irregular geometriescited by 3
13 more
  1. 2025TabKAN: Advancing Tabular Data Analysis using Kolmogorov-Arnold Networkcited by 3
  2. 2025iTFKAN: Interpretable Time Series Forecasting with Kolmogorov-Arnold Networkcited by 2
  3. 2025Efficiency Bottlenecks of Convolutional Kolmogorov-Arnold Networks: A Comprehensive Scrutiny with ImageNet, AlexNet, LeNet and Tabular Classificationcited by 1
  4. 2025Enhancing Federated Learning with Kolmogorov-Arnold Networks: A Comparative Study Across Diverse Aggregation Strategiescited by 1
  5. 2026RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basiscited by 1
  6. 2024DP-KAN: Differentially Private Kolmogorov-Arnold Networkscited by 0
  7. 2025HKAN: Hierarchical Kolmogorov-Arnold Network without Backpropagationcited by 0
  8. 2025"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understandingcited by 0
  9. 2025Kolmogorov Arnold Networks (KANs) for Imbalanced Data -- An Empirical Perspectivecited by 0
  10. 2025KARMA: Efficient Structural Defect Segmentation via Kolmogorov-Arnold Representation Learningcited by 0
  11. 2025PIKAN: Physics-Inspired Kolmogorov-Arnold Networks for Explainable UAV Channel Modellingcited by 0
  12. 2026KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognitioncited by 0
  13. 2026Is the Statistical Advantage Worth the Cost? An Empirical Comparison of KANs and MLPs for Structured Data Classificationcited by 0