Convolutional Kolmogorov-Arnold Networks
This offers a parameter-efficient alternative for deep learning models, though it appears incremental as it builds on existing KAN architecture.
The paper tackles the problem of parameter inefficiency in convolutional neural networks by introducing Convolutional Kolmogorov-Arnold Networks, which integrate learnable spline-based activation functions into convolutional layers. The result is competitive accuracy on Fashion-MNIST with up to 50% fewer parameters compared to baseline CNNs.
In this paper, we present Convolutional Kolmogorov-Arnold Networks, a novel architecture that integrates the learnable spline-based activation functions of Kolmogorov-Arnold Networks (KANs) into convolutional layers. By replacing traditional fixed-weight kernels with learnable non-linear functions, Convolutional KANs offer a significant improvement in parameter efficiency and expressive power over standard Convolutional Neural Networks (CNNs). We empirically evaluate Convolutional KANs on the Fashion-MNIST dataset, demonstrating competitive accuracy with up to 50% fewer parameters compared to baseline classic convolutions. This suggests that the KAN Convolution can effectively capture complex spatial relationships with fewer resources, offering a promising alternative for parameter-efficient deep learning models.