AI RESEARCH
GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modeling
arXiv CS.CV
•
ArXi:2511.05477v2 Announce Type: replace Medical image segmentation demands models that achieve high accuracy while maintaining computational efficiency and clinical interpretability. While recent Kolmogoro-Arnold Networks (KANs) offer powerful adaptive non-linearities, their full-channel spline transformations incur a quadratic parameter growth of $\mathcal{O}(C^{2}(G+k))$ with respect to the channel dimension $C$, where $G$ and $k$ denote the number of grid intervals and spline polynomial order, respectively.