# PRKAN: Parameter-Reduced Kolmogorov-Arnold Networks

arXiv: https://arxiv.org/abs/2501.07032 · HTML: https://mlsanity.com/paper/2501.07032/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2025.

## Built on by (most cited first, 7 of 7)

- [AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning](https://mlsanity.com/paper/2503.06112/) (2025)
- [Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2604.03345/) (2026)
- [RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis](https://mlsanity.com/paper/2609.01729/) (2026)
- [TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentation](https://mlsanity.com/paper/2505.18525/) (2025)
- [SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference](https://mlsanity.com/paper/2512.15742/) (2025)
- [Evaluating the Effectiveness of SechKAN on 1D Data](https://mlsanity.com/paper/2609.25876/) (2026)
- [Sample-Efficiency of Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2610.10627/) (2026)

## Abstract (arXiv)

Kolmogorov-Arnold Networks (KANs) represent an innovation in neural network architectures, offering a compelling alternative to Multi-Layer Perceptrons (MLPs) in models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. By advancing network design, KANs drive groundbreaking research and enable transformative applications across various scientific domains involving neural networks. However, existing KANs often require significantly more parameters in their network layers than MLPs. To address this limitation, this paper introduces PRKANs (Parameter-Reduced Kolmogorov-Arnold Networks), which employ several methods to reduce the parameter count in KAN layers, making them comparable to MLP layers. Experimental results on the MNIST and Fashion-MNIST datasets demonstrate that PRKANs outperform several existing KANs, and their variant with attention mechanisms rivals the performance of MLPs, albeit with slightly longer training times. Furthermore, the study highlights the advantages of Gaussian Radial Basis Functions (GRBFs) and layer normalization in KAN designs. The repository for this work is available at: https://github.com/hoangthangta/All-KAN.