Towards Interpretable Deep Neural Networks for Tabular Data

Khawla Elhadri, Jörg Schlötterer, Christin Seifert

Track: Extended Abstract Track

Keywords: Deep Neural Networks, Explainability in neural networks for tabular data

Abstract:

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 comparable to that of state-of-the-art, black-box neural models and classical machine learning approaches while being fully interpretable.

Submission Number: 121