AI RESEARCH
FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
arXiv CS.LG
•
ArXi:2509.24472v3 Announce Type: replace Permutation equivariant neural networks employing parameter-sharing schemes have emerged as powerful models for leveraging a wide range of data symmetries, significantly enhancing the generalization and computational efficiency of the resulting models. Recently, Kolmogoro-Arnold Networks (KANs) have nstrated promise through their improved interpretability and expressivity compared to traditional architectures based on MLPs.