Attribution-Scores in Data Management and Explainable Machine Learning
Abstract
We describe recent research on the use of actual causality in the definition of responsibility scores as explanations for query answers in databases, and for outcomes from classification models in machine learning. In the case of databases, useful connections with database repairs are illustrated and exploited. Repairs are also used to give a quantitative measure of the consistency of a database. For classification models, the responsibility score is properly extended and illustrated. The efficient computation of Shap-score is also analyzed and discussed. The emphasis is placed on work done by the author and collaborators.
Cite
@article{arxiv.2308.00184,
title = {Attribution-Scores in Data Management and Explainable Machine Learning},
author = {Leopoldo Bertossi},
journal= {arXiv preprint arXiv:2308.00184},
year = {2023}
}
Comments
Paper associated to ADBIS23 tutorial. To appear. arXiv admin note: substantial text overlap with arXiv:2303.02829, arXiv:2106.10562