Fecha
2026-06-10
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editorial
Elsevier
Resumen
Deep neural networks excel in vision and language but often struggle with tabular data due to weak inductive biases and limited interpretability. While converting tabular data into synthetic images enables Convolutional Neural Networks (CNNs) to exploit spatial feature interactions, this approach typically exacerbates the models’ black-box nature. To achieve both high predictive power and transparent decision-making, we propose an interpretable Hybrid Neural Network that integrates visual reasoning (CNNs applied to synthetic images) with symbolic learning (Kolmogorov-Arnold Networks (KAN) applied to tabular data). Extensive evaluations across diverse datasets demonstrate that our CNN–KAN hybrids achieve highly competitive, and often superior, predictive performance. To audit their internal reasoning, we introduce the Global Feature Score (GFS), a unified metric that aggregates spatial saliency from Grad-CAM with symbolic attributions from the KAN branch, producing consistent feature relevance rankings. By explicitly diagnosing modality dominance, layout artifact sensitivity, and inter-branch agreement, the proposed framework significantly reduces reliance on fragile post-hoc methods. Ultimately, embedding interpretability directly into the architecture provides auditable, cross-verified explanations, establishing a robust foundation for Responsible AI-oriented tabular learning.
Descripción
The registered version of this article, first published in Information Processing & Management, is available online at the publisher's website: EDITOR, https://doi.org/10.1016/j.ipm.2026.104954
La versión registrada de este artículo, publicado por primera vez en Information Processing & Management, está disponible en línea en el sitio web del editor: EDITOR, https://doi.org/10.1016/j.ipm.2026.104954
La versión registrada de este artículo, publicado por primera vez en Information Processing & Management, está disponible en línea en el sitio web del editor: EDITOR, https://doi.org/10.1016/j.ipm.2026.104954
Categorías UNESCO
Palabras clave
Synthetic images, Tabular-to-image, Hybrid Neural Networks, EXplainable Artificial Intelligence (XAI), Synthetic data, Dual-stream interpretability, TINTOlib
Citación
Mondragon-Ruiz, G., Liu, J., Castillo-Cara, M., & García-Castro, R. (2026). Interpretable CNN-KAN hybrid architectures for tabular data with synthetic image encoding. Information Processing & Management, 63(8), Artículo 104954[cite: 2, 3]. DOI: 10.1016/j.ipm.2026.104954.
Centro
E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial



