Work

An Empirical Comparison of Interpretable Models to Post-Hoc Explanations

Year: 2023
Type: article
Abstract: Recently, some effort went into explaining intransparent and black-box models, such as deep neural networks or random forests. So-called model-agnostic methods typically approximate the prediction of the intransparent black-box model with an interpretable model, without considering any specifics of the black-box model itself. It is a valid question whether direct learning of interpretable white-box models should not be preferred over post-hoc approximations of intransparent and black-box models. In this paper, we report the results of an empirical study, which compares post-hoc explanations and interpretable models on several datasets for rule-based and feature-based interpretable models. The results seem to underline that often directly learned interpretable models approximate the black-box models at least as well as their post-hoc surrogates, even though the former do not have direct access to the black-box model.
Source: AI
Language: English
Open Access status: gold
Estimated APC paid: $1,077
OpenAlex ID: W4377115400
FWCI: 1.067
Cites: 19
Cited by: 19
Related to: 10