Parisa Mahya, Johannes Fürnkranz,
"An Empirical Comparison of Interpretable Models to Post-Hoc Explanations"
, in AI, Vol. 4, Nummer 2, MDPI, Seite(n) 426-436, 2023, ISSN: 2673-2688
Original Titel:
An Empirical Comparison of Interpretable Models to Post-Hoc Explanations
Sprache des Titels:
Englisch
Original Kurzfassung:
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.
Sprache der Kurzfassung:
Englisch
Journal:
AI
Veröffentlicher:
MDPI
Volume:
4
Number:
2
Seitenreferenz:
426-436
Erscheinungsjahr:
2023
ISSN:
2673-2688
Anzahl der Seiten:
11
Notiz zur Publikation:
Special Issue on Interpretable and Explainable AI Applications