Towards Interpretable Deep Neural Networks for Tabular Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Elhadri, Khawla, Schlötterer, Jörg, Seifert, Christin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915892019855360
author Elhadri, Khawla
Schlötterer, Jörg
Seifert, Christin
author_facet Elhadri, Khawla
Schlötterer, Jörg
Seifert, Christin
contents Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows us to represent predictions as linear combinations of semantically meaningful components. Empirical evaluations demonstrate that XNNTab attains performance on par with or exceeding that of state-of-the-art, black-box neural models and classical machine learning approaches while being fully interpretable.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08617
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Interpretable Deep Neural Networks for Tabular Data
Elhadri, Khawla
Schlötterer, Jörg
Seifert, Christin
Machine Learning
Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows us to represent predictions as linear combinations of semantically meaningful components. Empirical evaluations demonstrate that XNNTab attains performance on par with or exceeding that of state-of-the-art, black-box neural models and classical machine learning approaches while being fully interpretable.
title Towards Interpretable Deep Neural Networks for Tabular Data
topic Machine Learning
url https://arxiv.org/abs/2509.08617