Geometric Kolmogorov--Arnold Network (GeoKAN)

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sen, Abhijit, Parida, Bikram Keshari, Maiti, Giridas, Arya, Mahima, Bondar, Denys I.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913099366268928
author Sen, Abhijit
Parida, Bikram Keshari
Maiti, Giridas
Arya, Mahima
Bondar, Denys I.
author_facet Sen, Abhijit
Parida, Bikram Keshari
Maiti, Giridas
Arya, Mahima
Bondar, Denys I.
contents We introduce Geometric Kolmogorov--Arnold Networks (GeoKANs), a family of geometry-aware KAN-type models in which approximation is carried out in learned, geometry-adapted coordinates rather than in fixed Euclidean input coordinates. GeoKAN achieves this by learning a diagonal Riemannian metric that warps the input before basis expansion and feature mixing. The learned metric provides a geometric inductive bias through local length scaling and volume distortion, and in physics-informed settings it also affects the differential structure seen by the model. Within this framework, we develop three main variants, namely GeoKAN-NNMetric, GeoKAN-$γ$, and LM-KAN. For LM-KAN, we further consider three basis-specific versions, LM-KAN-RBF, LM-KAN-Wav, and LM-KAN-Fourier. These variants allow us to study geometry-aware KAN models both as general function approximators and as surrogates in physics-informed learning. By stretching regions with rapid variation and compressing smoother regions, GeoKAN reallocates representational resolution in a task-dependent manner, allowing the model to place capacity where it is most needed. As a result, GeoKAN is well suited to sharp, stiff, localized, and strongly non-uniform regimes arising in scientific machine learning and differential-equation problems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06740
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geometric Kolmogorov--Arnold Network (GeoKAN)
Sen, Abhijit
Parida, Bikram Keshari
Maiti, Giridas
Arya, Mahima
Bondar, Denys I.
Machine Learning
Artificial Intelligence
We introduce Geometric Kolmogorov--Arnold Networks (GeoKANs), a family of geometry-aware KAN-type models in which approximation is carried out in learned, geometry-adapted coordinates rather than in fixed Euclidean input coordinates. GeoKAN achieves this by learning a diagonal Riemannian metric that warps the input before basis expansion and feature mixing. The learned metric provides a geometric inductive bias through local length scaling and volume distortion, and in physics-informed settings it also affects the differential structure seen by the model. Within this framework, we develop three main variants, namely GeoKAN-NNMetric, GeoKAN-$γ$, and LM-KAN. For LM-KAN, we further consider three basis-specific versions, LM-KAN-RBF, LM-KAN-Wav, and LM-KAN-Fourier. These variants allow us to study geometry-aware KAN models both as general function approximators and as surrogates in physics-informed learning. By stretching regions with rapid variation and compressing smoother regions, GeoKAN reallocates representational resolution in a task-dependent manner, allowing the model to place capacity where it is most needed. As a result, GeoKAN is well suited to sharp, stiff, localized, and strongly non-uniform regimes arising in scientific machine learning and differential-equation problems.
title Geometric Kolmogorov--Arnold Network (GeoKAN)
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.06740