AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning
Preprint
Abstract
Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems, with the potential to replace Multilayer Perceptrons (MLPs). While many KANs are designed using basis and polynomial functions, such as B-splines, ReLU-KAN utilizes a combination of ReLU functions to mimic the structure of B-splines and take advantage of ReLU's speed. However, ReLU-KAN is not built for multiple inputs, and its limitations stem from ReLU's handling of negative values, which can restrict feature extraction. To address these issues, we introduce Activation Function-Based Kolmogorov-Arnold Networks (AF-KAN), expanding ReLU-KAN with various activations and their function combinations. This novel KAN also incorporates parameter reduction methods, primarily attention mechanisms and data normalization, to enhance performance on image classification datasets. We explore different activation functions, function combinations, grid sizes, and spline orders to validate the effectiveness of AF-KAN and determine its optimal configuration. In the experiments, AF-KAN significantly outperforms MLP, ReLU-KAN, and other KANs with the same parameter count. It also remains competitive even when using fewer than 6 to 10 times the parameters while maintaining the same network structure. However, AF-KAN requires a longer training time and consumes more FLOPs. The repository for this work is available at https://github.com/hoangthangta/All-KAN.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- FC-KAN: Function combinations in Kolmogorov-Arnold networksInformation Sciences, 2026
- TC-KANRecon: High-Quality and Accelerated MRI Reconstruction via Adaptive KAN Mechanisms and Intelligent Feature ScalingIEEE Journal of Biomedical and Health Informatics, 2025
- EFKAN: A KAN-integrated neural operator for efficient magnetotelluric forward modelingComputers & Geosciences, 2025
- CoxKAN: Kolmogorov-Arnold networks for interpretable, high-performance survival analysisBioinformatics, 2025
- BSRBF-KAN: A Combination of B-Splines and Radial Basis Functions in Kolmogorov-Arnold Networks2025
- Effective Integration of KAN for Keyword Spotting2025
- CKAN: Convolutional Kolmogorov–Arnold Networks Model for Intrusion Detection in IoT EnvironmentIEEE Access, 2024
- The Kolmogorov–Arnold representation theorem revisitedNeural Networks, 2021
- Sigmoid-weighted linear units for neural network function approximation in reinforcement learningNeural Networks, 2018
- The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]IEEE Signal Processing Magazine, 2012