Explaining any black box model using real data
Frontiers in Computer Science · 08.08.2023 · 5
DOI: 10.3389/fcomp.2023.1143904 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Computer Science, online erschienen am 08.08.2023. Verfasst von Anton Björklund und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Academy of Finland.
Abstract (Originalsprache)
In recent years the use of complex machine learning has increased drastically. These complex black box models trade interpretability for accuracy. The lack of interpretability is troubling for, e.g., socially sensitive, safety-critical, or knowledge extraction applications. In this paper, we propose a new explanation method, SLISE, for interpreting predictions from black box models. SLISE can be used with any black box model (model-agnostic), does not require any modifications to the black box model ( post-hoc ), and explains individual predictions (local). We evaluate our method using real-world datasets and compare it against other model-agnostic, local explanation methods. Our approach solves shortcomings in other related explanation methods by only using existing data instead of sampling new, artificial data. The method also generates more generalizable explanations and is usable without modification across various data domains.
Förderung
- Academy of Finland
Zitieren
APA
Björklund, A., Henelius, A., Oikarinen, E., Kallonen, K., & Puolamäki, K. (2023). Explaining any black box model using real data. Frontiers in Computer Science, 5. https://doi.org/10.3389/fcomp.2023.1143904
Vancouver
Björklund A, Henelius A, Oikarinen E, Kallonen K, Puolamäki K. Explaining any black box model using real data. Frontiers in Computer Science. 2023;5. doi:10.3389/fcomp.2023.1143904
BibTeX
@article{Bjrklund2023,
author = {Björklund, Anton and Henelius, Andreas and Oikarinen, Emilia and Kallonen, Kimmo and Puolamäki, Kai},
title = {Explaining any black box model using real data},
journal = {Frontiers in Computer Science},
year = {2023},
volume = {5},
doi = {10.3389/fcomp.2023.1143904}
}
EUVIMED