InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation

TL;DR

InterpreTabNet enhances neural network interpretability for tabular data by modeling attention as a sparse, latent variable, enabling clearer feature importance insights and improved predictive performance.

Contribution

This paper introduces InterpreTabNet, a novel variant of TabNet that uses Gumbel-Softmax sampling and KL regularization to produce sparse, interpretable attention masks.

Findings

Outperforms previous interpretability methods on real datasets

Achieves higher feature sparsity and clarity in explanations

Maintains competitive predictive accuracy

Abstract

Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred attention masks are often dense, making it challenging to come up with rationales about the predictive signal. To remedy this, we propose InterpreTabNet, a variant of the TabNet model that models the attention mechanism as a latent variable sampled from a Gumbel-Softmax distribution. This enables us to regularize the model to learn distinct concepts in the attention masks via a KL Divergence regularizer. It prevents overlapping feature selection by promoting sparsity which maximizes the model's efficacy and improves interpretability to determine the important features when predicting the outcome. To assist in the interpretation of feature interdependencies from our model, we employ a large language model (GPT-4) and use prompt engineering to map from the learned feature mask onto natural language text describing the learned signal. Through comprehensive experiments on real-world datasets, we demonstrate that InterpreTabNet outperforms previous methods for interpreting tabular data while attaining competitive accuracy.