Contrasting Explanations for Understanding and Regularizing Model Adaptations

Artelt A, Hinder F, Vaquet V, Feldhans R, Hammer B (2022)
Neural Processing Letters.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Abstract / Bemerkung
Many of today’s decision making systems deployed in the real world are not static—they are changing and adapting over time, a phenomenon known as model adaptation takes place. Because of their wide reaching influence and potentially serious consequences, the need for transparency and interpretability of AI-based decision making systems is widely accepted and thus have been worked on extensively—e.g. a very prominent class of explanations are contrasting explanations which try to mimic human explanations. However, usually, explanation methods assume a static system that has to be explained. Explaining non-static systems is still an open research question, which poses the challenge how to explain model differences, adaptations and changes. In this contribution, we propose and (empirically) evaluate a general framework for explaining model adaptations and differences by contrasting explanations. We also propose a method for automatically finding regions in data space that are affected by a given model adaptation—i.e. regions where the internal reasoning of the other (e.g. adapted) model changed—and thus should be explained. Finally, we also propose a regularization for model adaptations to ensure that the internal reasoning of the adapted model does not change in an unwanted way.
Erscheinungsjahr
2022
Zeitschriftentitel
Neural Processing Letters
ISSN
1370-4621
eISSN
1573-773X
Page URI
https://pub.uni-bielefeld.de/record/2962746

Zitieren

Artelt A, Hinder F, Vaquet V, Feldhans R, Hammer B. Contrasting Explanations for Understanding and Regularizing Model Adaptations. Neural Processing Letters. 2022.
Artelt, A., Hinder, F., Vaquet, V., Feldhans, R., & Hammer, B. (2022). Contrasting Explanations for Understanding and Regularizing Model Adaptations. Neural Processing Letters. https://doi.org/10.1007/s11063-022-10826-5
Artelt, A., Hinder, F., Vaquet, V., Feldhans, R., and Hammer, B. (2022). Contrasting Explanations for Understanding and Regularizing Model Adaptations. Neural Processing Letters.
Artelt, A., et al., 2022. Contrasting Explanations for Understanding and Regularizing Model Adaptations. Neural Processing Letters.
A. Artelt, et al., “Contrasting Explanations for Understanding and Regularizing Model Adaptations”, Neural Processing Letters, 2022.
Artelt, A., Hinder, F., Vaquet, V., Feldhans, R., Hammer, B.: Contrasting Explanations for Understanding and Regularizing Model Adaptations. Neural Processing Letters. (2022).
Artelt, André, Hinder, Fabian, Vaquet, Valerie, Feldhans, Robert, and Hammer, Barbara. “Contrasting Explanations for Understanding and Regularizing Model Adaptations”. Neural Processing Letters (2022).
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Link(s) zu Volltext(en)
Access Level
OA Open Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Suchen in

Google Scholar