Computing Probabilistic Explanations for ML Models: Fixed-Parameter Algorithms
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24622-24629
DOI: 10.1609/aaai.v40i29.39646 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sebastian Ordyniak und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Machine learning models now drive many critical decisions, making explanations of their reasoning essential. Recent work analyzes the complexity of exact explanations in transparent models, but these explanations are often too large for practical use. This has motivated research into probabilistic alternatives. We study probabilistic extensions that allow controlled uncertainty while maintaining rigorous foundations. We analyze three basic model types: decision trees, decision lists, and decision sets. We introduce algorithms for computing both local and global probabilistic explanations for these models. Our main result shows that computing minimum-size probabilistic explanations is fixed-parameter tractable when parameterized by structural properties---specifically, the number of terms for decision lists and decision sets and the minimum of the number of positive and the number of negative leaves.
Zitieren
APA
Ordyniak, S., Rychlicki, M., & Szeider, S. (2026). Computing Probabilistic Explanations for ML Models: Fixed-Parameter Algorithms. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24622-24629. https://doi.org/10.1609/aaai.v40i29.39646
Vancouver
Ordyniak S, Rychlicki M, Szeider S. Computing Probabilistic Explanations for ML Models: Fixed-Parameter Algorithms. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24622-24629. doi:10.1609/aaai.v40i29.39646
BibTeX
@article{Ordyniak2026,
author = {Ordyniak, Sebastian and Rychlicki, Mateusz and Szeider, Stefan},
title = {Computing Probabilistic Explanations for ML Models: Fixed-Parameter Algorithms},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {29},
pages = {24622--24629},
doi = {10.1609/aaai.v40i29.39646}
}
EUVIMED