An ASP-based approach to counterfactual explanations for classification
From MaRDI portal
Publication:1995447
DOI10.1007/978-3-030-57977-7_5zbMATH Open1478.68344arXiv2004.13237OpenAlexW3082833989MaRDI QIDQ1995447FDOQ1995447
Publication date: 23 February 2021
Abstract: We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to decisions produced by classification models. They can be applied with black-box models and models that can be specified as logic programs, such as rule-based classifiers. The main focus in on the specification and computation of maximum responsibility causal explanations. The use of additional semantic knowledge is investigated.
Full work available at URL: https://arxiv.org/abs/2004.13237
Cited In (4)
- Answer-set programs for reasoning about counterfactual interventions and responsibility scores for classification
- Score-based explanations in data management and machine learning: an answer-set programming approach to counterfactual analysis
- A Symbolic Approach for Counterfactual Explanations
- Declarative reasoning on explanations using constraint logic programming
Recommendations
- Score-based explanations in data management and machine learning: an answer-set programming approach to counterfactual analysis 👍 👎
- A unified logical framework for explanations in classifier systems 👍 👎
- Title not available (Why is that?) 👍 👎
- A Symbolic Approach for Counterfactual Explanations 👍 👎
- A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C 👍 👎
- Answer-set programs for reasoning about counterfactual interventions and responsibility scores for classification 👍 👎
- Tractability of explaining classifier decisions 👍 👎
This page was built for publication: An ASP-based approach to counterfactual explanations for classification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1995447)
