Interpretable Mesomorphic Networks for Tabular Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kadra, Arlind, Arango, Sebastian Pineda, Grabocka, Josif
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916460186566656
author Kadra, Arlind
Arango, Sebastian Pineda
Grabocka, Josif
author_facet Kadra, Arlind
Arango, Sebastian Pineda
Grabocka, Josif
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2305_13072
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Interpretable Mesomorphic Networks for Tabular Data
Kadra, Arlind
Arango, Sebastian Pineda
Grabocka, Josif
Machine Learning
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.
title Interpretable Mesomorphic Networks for Tabular Data
topic Machine Learning
url https://arxiv.org/abs/2305.13072