mlsanityData to 7 Oct 2026

Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysis

arXiv 2106.10562 ↗First posted 19 Jun 2021cs.AI cs.DB cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 59 references that are in the map. First posted on arXiv 19 Jun 2021.

Builds on

17 of 59 references.

References · 17

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2020On the Tractability of SHAP Explanationscited by 92
  3. 2015A Modification of the Halpern-Pearl Definition of Causalitycited by 47
  4. 2018An Interpretable Model with Globally Consistent Explanations for Credit Riskcited by 33
  5. 2020Causality-based Explanation of Classification Outcomescited by 25
  6. 2019The Shapley Value of Tuples in Query Answeringcited by 23
  7. 2020Declarative Approaches to Counterfactual Explanations for Classificationcited by 14
  8. 2014From Causes for Database Queries to Repairs and Model-Based Diagnosis and Backcited by 13
  9. 2016Complexity of Consistent Query Answering in Databases under Cardinality-Based and Incremental Repair Semantics (extended version)cited by 12
  10. 2016Quantifying Causal Effects on Query Answering in Databasescited by 10
  11. 2020An ASP-Based Approach to Counterfactual Explanations for Classificationcited by 10
  12. 2016Causes for Query Answers from Databases: Datalog Abduction, View-Updates, and Integrity Constraintscited by 8
5 more
  1. 2020The Shapley Value of Inconsistency Measures for Functional Dependenciescited by 8
  2. 2019The Impact of Negation on the Complexity of the Shapley Value in Conjunctive Queriescited by 6
  3. 2020The Tractability of SHAP-Score-Based Explanations over Deterministic and Decomposable Boolean Circuitscited by 4
  4. 2018Repair-Based Degrees of Database Inconsistency: Computation and Complexitycited by 2
  5. 2019Explaining Predictions from Tree-based Boosting Ensemblescited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1.

2 papers.

  1. 2023Attribution-Scores and Causal Counterfactuals as Explanations in Artificial Intelligencecited by 2
  2. 2022Answer-Set Programs for Repair Updates and Counterfactual Interventionscited by 0