AI summaryⓘ
The authors developed TabSOM, a new way to turn spreadsheet-like data into images so computers can better understand it using vision-based AI models. Unlike previous methods that only considered individual data points, TabSOM arranges features in fixed positions while also capturing relationships between them using a special map called a Self-Organizing Map (SOM). This helps the AI not only predict well but also explain which features are important. Their tests showed TabSOM performed consistently well compared to other methods, and its explanations matched traditional techniques while adding new insights. Overall, the authors propose a method that balances accuracy and interpretability when applying deep learning to tabular data.
Tabular dataSelf-Organizing Map (SOM)Dimensionality reductionConvolutional neural networksVision transformersFeature relationshipsPartial dependence plotClass-separation importance scoreRandom ForestSHAP
Authors
David Chushig-Muzo, María Ángeles Rodríguez de Cara, Eva Milara, Francisco J. Lara-Abelenda, Luis Zhinin-Vera, Diego H. Peluffo-Ordóñez
Abstract
Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They convert tabular data into image representations, mapping each feature at a fixed pixel location derived from a dimensionality-reduction method (e.g., t-SNE, UMAP, PCA). However, they encode only the marginal value of each feature and discard information about feature relationships. We propose TabSOM, a tabular-to-image encoding built on the Self-Organizing Map (SOM), which provides: (i) a spatial layout in which every input feature occupies a fixed canvas position derived from its component plane via collision-free Hungarian assignment; and (ii) a graph that captures pairwise feature relationships derived from the SOM component planes. The resulting image stacks two multi-scale node channels: one encodes feature values at fixed scales, while the other encodes pairwise feature interactions as spatial connections between related features. Two SOM-derived interpretability approaches are introduced: a prototype-inspired partial dependence plot and a class--separation importance score. Benchmarked against twelve existing tabular-to-image methods across public binary-classification datasets, TabSOM ranks first or second on every dataset and achieves the lowest variance of any method evaluated. Interpretability obtained with TabSOM was validated against Random Forest, XGBoost, and SHAP, the class-separation score shows reasonable agreement with established baselines on the top-ranked features while capturing complementary structural information from input data. These results demonstrate that TabSOM provides an effective and interpretable approach for applying deep learning architectures to tabular data, bridging the performance--interpretability gap in this domain.