Score-based explanations in data management and machine learning: an answer-set programming approach to counterfactual analysis

DOI10.1007/978-3-030-95481-9_7MaRDI QIDQ6166581zbMATH OpenOpenAlexFDO

Authors Leopoldo Bertossi

Publication date 3 August 2023

Published in Reasoning Web. Declarative Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2106.10562

Mathematics Subject Classification ID

Logic programming (68N17) Database theory (68P15)

Abstract: We describe some recent approaches to score-based explanations for query answers in databases and outcomes from classification models in machine learning. The focus is on work done by the author and collaborators. Special emphasis is placed on declarative approaches based on answer-set programming to the use of counterfactual reasoning for score specification and computation. Several examples that illustrate the flexibility of these methods are shown.

Recommendations

• Score-Based Explanations in Data Management and Machine Learning
• Answer-set programs for reasoning about counterfactual interventions and responsibility scores for classification
• An ASP-based approach to counterfactual explanations for classification
• Contrastive explanations for answer-set programs

Cites work

• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• scientific article; zbMATH DE number 25190 (Why is no real title available?)
• scientific article; zbMATH DE number 44384 (Why is no real title available?)
• scientific article; zbMATH DE number 1179314 (Why is no real title available?)
• scientific article; zbMATH DE number 2080480 (Why is no real title available?)
• scientific article; zbMATH DE number 7566076 (Why is no real title available?)
• scientific article; zbMATH DE number 7407794 (Why is no real title available?)
• scientific article; zbMATH DE number 2243367 (Why is no real title available?)
• scientific article; zbMATH DE number 3078997 (Why is no real title available?)
• Algorithmic Game Theory
• An ASP-based approach to counterfactual explanations for classification
• Answer sets for consistent query answering in inconsistent databases
• Causes and Explanations: A Structural-Model Approach. Part I: Causes
• Causes for query answers from databases: datalog abduction, view-updates, and integrity constraints
• Computable Functions in ASP: Theory and Implementation
• Computational Complexity
• From causes for database queries to repairs and model-based diagnosis and back
• On the Complexity of Cooperative Solution Concepts
• On the Tractability of SHAP Explanations
• On the measure of conflicts: Shapley inconsistency values
• Probabilistic databases
• Programming with non-determinism in deductive databases
• Repair-based degrees of database inconsistency
• The DLV system for knowledge representation and reasoning
• The Shapley value for cooperative games under precedence constraints

Cited in

(3)

• An ASP-based approach to counterfactual explanations for classification
• Score-Based Explanations in Data Management and Machine Learning
• Answer-set programs for reasoning about counterfactual interventions and responsibility scores for classification

This page was built for publication: Score-based explanations in data management and machine learning: an answer-set programming approach to counterfactual analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6166581)