Enregistré dans:
Détails bibliographiques
Auteurs principaux: De la Fuente, Luis A., Moreno, Hernan A., Alvarez, Laura V., Gupta, Hoshin V.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.15755
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909968327770112
author De la Fuente, Luis A.
Moreno, Hernan A.
Alvarez, Laura V.
Gupta, Hoshin V.
author_facet De la Fuente, Luis A.
Moreno, Hernan A.
Alvarez, Laura V.
Gupta, Hoshin V.
contents Interpreting complex datasets remains a major challenge for scientists, particularly due to high dimensionality and collinearity among variables. We introduce a novel application of Kolmogorov-Arnold Networks (KANs) to enhance interpretability and parsimony beyond what traditional correlation analyses offer. We present two interpretable, color-coded visualization tools: the Pairwise KAN Matrix (PKAN) and the Multivariate KAN Contribution Matrix (MKAN). PKAN characterizes nonlinear associations between pairs of variables, while MKAN serves as a nonlinear feature-ranking tool that quantifies the relative contributions of inputs in predicting a target variable. These tools support pre-processing (e.g., feature selection, redundancy analysis) and post-processing (e.g., model explanation, physical insights) in model development workflows. Through experimental comparisons, we demonstrate that PKAN and MKAN yield more robust and informative results than Pearson Correlation and Mutual Information. By capturing the strength and functional forms of relationships, these matrices facilitate the discovery of hidden physical patterns and promote domain-informed model development.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15755
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KAN-Matrix: Visualizing Nonlinear Pairwise and Multivariate Contributions for Physical Insight
De la Fuente, Luis A.
Moreno, Hernan A.
Alvarez, Laura V.
Gupta, Hoshin V.
Machine Learning
Applied Physics
Data Analysis, Statistics and Probability
Interpreting complex datasets remains a major challenge for scientists, particularly due to high dimensionality and collinearity among variables. We introduce a novel application of Kolmogorov-Arnold Networks (KANs) to enhance interpretability and parsimony beyond what traditional correlation analyses offer. We present two interpretable, color-coded visualization tools: the Pairwise KAN Matrix (PKAN) and the Multivariate KAN Contribution Matrix (MKAN). PKAN characterizes nonlinear associations between pairs of variables, while MKAN serves as a nonlinear feature-ranking tool that quantifies the relative contributions of inputs in predicting a target variable. These tools support pre-processing (e.g., feature selection, redundancy analysis) and post-processing (e.g., model explanation, physical insights) in model development workflows. Through experimental comparisons, we demonstrate that PKAN and MKAN yield more robust and informative results than Pearson Correlation and Mutual Information. By capturing the strength and functional forms of relationships, these matrices facilitate the discovery of hidden physical patterns and promote domain-informed model development.
title KAN-Matrix: Visualizing Nonlinear Pairwise and Multivariate Contributions for Physical Insight
topic Machine Learning
Applied Physics
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2512.15755