Explaintable: Explaining Large Scale Models Applied to Tabular Data
Abstract
Interpretability of Deep Neural Networks (DNNs) is crucial when designing reliable and trustworthy models. However, there is a lack of interpretability methods for DNNs applied to tabular data. In this short paper, we propose a novel feature importance method for any Tabular Deep Learning model based on activation maximization. This allows to discard uninformative features for the network. We present some preliminary results on one of the largest scale Tabular Networks. In addition, we suggest how it can be applied to Large Language Models (LLM) to systematically study their biases too.
Cite
Text
Bautiste et al. "Explaintable: Explaining Large Scale Models Applied to Tabular Data." ICLR 2023 Workshops: RTML, 2023.Markdown
[Bautiste et al. "Explaintable: Explaining Large Scale Models Applied to Tabular Data." ICLR 2023 Workshops: RTML, 2023.](https://mlanthology.org/iclrw/2023/bautiste2023iclrw-explaintable/)BibTeX
@inproceedings{bautiste2023iclrw-explaintable,
title = {{Explaintable: Explaining Large Scale Models Applied to Tabular Data}},
author = {Bautiste, Javier Sanguino and Engelmann, Tim and Montemayor, Natalia Pato and Hart, Louis and Lanzillotta, Giulia and Bachmann, Gregor and Hofmann, Thomas},
booktitle = {ICLR 2023 Workshops: RTML},
year = {2023},
url = {https://mlanthology.org/iclrw/2023/bautiste2023iclrw-explaintable/}
}