AMAKAN: Fully Interpretable Adaptive Multiscale Attention Through Kolmogorov-Arnold Networks

Felice Franchini, Stefano Galantucci

2025

Abstract

This paper introduces AMAKAN, a novel method for tabular data classification combining the Adaptive Multi-scale Deep Neural Network with Kolmogorov–Arnold Network to ensure full interpretability without sacrificing predictive performance. The Adaptive Multiscale Deep Neural Network dynamically focuses on relevant features at different scales by using learned attention mechanisms. These multiscale features are then refined by Kolmogorov–Arnold Network layers, which replace typical dense layers with learnable univariate functions on network edges, providing transparency by allowing practitioners to visually see and inspect feature transformations directly. Experimental results on a variety of real-world datasets demonstrate that AMAKAN achieves performance equivalent to or better than state-of-the-art baselines while providing transparent and actionable explanations for its predictions. By the seamless combination of interpretable attention mechanisms with Kolmogorov–Arnold Network layers, the paper presents an explainable and efficient deep learning method for tabular data across a vast spectrum of application domains.

Paper Citation

in Harvard Style

Franchini F. and Galantucci S. (2025). AMAKAN: Fully Interpretable Adaptive Multiscale Attention Through Kolmogorov-Arnold Networks. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DMDH; ISBN 978-989-758-758-0, SciTePress, pages 800-808. DOI: 10.5220/0013654200003967

in Bibtex Style

@conference{dmdh25,
author={Felice Franchini and Stefano Galantucci},
title={AMAKAN: Fully Interpretable Adaptive Multiscale Attention Through Kolmogorov-Arnold Networks},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DMDH},
year={2025},
pages={800-808},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013654200003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DMDH
TI - AMAKAN: Fully Interpretable Adaptive Multiscale Attention Through Kolmogorov-Arnold Networks
SN - 978-989-758-758-0
AU - Franchini F.
AU - Galantucci S.
PY - 2025
SP - 800
EP - 808
DO - 10.5220/0013654200003967
PB - SciTePress