Interpretable Mesomorphic Networks for Tabular Data

TL;DR

This paper introduces mesomorphic neural networks that combine deep and linear models to provide high accuracy and inherent interpretability for tabular data, addressing the explainability gap in neural architectures.

Contribution

It proposes a novel class of interpretable neural networks that generate explainable linear models on a per-instance basis while maintaining deep learning performance.

Findings

Achieves comparable accuracy to state-of-the-art classifiers on tabular data.

Outperforms existing explainable-by-design methods.

Provides inherent interpretability without sacrificing performance.

Abstract

Even though neural networks have been long deployed in applications involving tabular data, still existing neural architectures are not explainable by design. In this paper, we propose a new class of interpretable neural networks for tabular data that are both deep and linear at the same time (i.e. mesomorphic). We optimize deep hypernetworks to generate explainable linear models on a per-instance basis. As a result, our models retain the accuracy of black-box deep networks while offering free-lunch explainability for tabular data by design. Through extensive experiments, we demonstrate that our explainable deep networks have comparable performance to state-of-the-art classifiers on tabular data and outperform current existing methods that are explainable by design.