Interpretable Mesomorphic Networks for Tabular Data

Arlind Kadra, Sebastian Pineda Arango, Josif Grabocka

Keywords: explainability, deep neural networks, tabular data, hypernetwork, interpretability, explainable benchmark, xai.

TL;DR: Explainable deep networks that are not only as accurate as their black-box deep-learning counterparts but also as interpretable as state-of-the-art explanation techniques.

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.

Primary Area: Interpretability and explainability

Submission Number: 535