Symbolic Explanations for Multi-Label Classification

Ryma Boumazouza, Fahima Cheikh-Alili, Bertrand Mazure, Karim Tabia

2023

Abstract

This paper proposes an agnostic and declarative approach to provide different types of symbolic explanations for multi-label classifiers. More precisely, in addition to global sufficient reason and counterfactual explanations, our approach makes it possible to generate explanations at different levels of granularity in addition to structural relationships between labels. Our approach is declarative and allows to take advantage of the strengths of modern SAT-based oracles and solvers. Our experimental study provides promising results on many multi-label datasets.

Paper Citation

in Harvard Style

Boumazouza R., Cheikh-Alili F., Mazure B. and Tabia K. (2023). Symbolic Explanations for Multi-Label Classification. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 342-349. DOI: 10.5220/0011668700003393

in Bibtex Style

@conference{icaart23,
author={Ryma Boumazouza and Fahima Cheikh-Alili and Bertrand Mazure and Karim Tabia},
title={Symbolic Explanations for Multi-Label Classification},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={342-349},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011668700003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Symbolic Explanations for Multi-Label Classification
SN - 978-989-758-623-1
AU - Boumazouza R.
AU - Cheikh-Alili F.
AU - Mazure B.
AU - Tabia K.
PY - 2023
SP - 342
EP - 349
DO - 10.5220/0011668700003393