Answer-set programs for reasoning about counterfactual interventions and responsibility scores for classification

From MaRDI portal
Publication:6166547

DOI10.1007/978-3-030-97454-1_4zbMATH Open1524.68349arXiv2107.10159OpenAlexW3186753874MaRDI QIDQ6166547

Gabriela Reyes, Leopoldo Bertossi

Publication date: 3 August 2023

Published in: Inductive Logic Programming (Search for Journal in Brave)

Abstract: We describe how answer-set programs can be used to declaratively specify counterfactual interventions on entities under classification, and reason about them. In particular, they can be used to define and compute responsibility scores as attribution-based explanations for outcomes from classification models. The approach allows for the inclusion of domain knowledge and supports query answering. A detailed example with a naive-Bayes classifier is presented.


Full work available at URL: https://arxiv.org/abs/2107.10159





Cites Work


Cited In (1)






This page was built for publication: Answer-set programs for reasoning about counterfactual interventions and responsibility scores for classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6166547)