An efficient explanation of individual classifications using game theory

zbMATH Open1242.68250MaRDI QIDQ2896017FDOQ2896017

Authors: Erik Štrumbelj, Igor Kononenko 

Publication date: 13 July 2012

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: http://www.jmlr.org/papers/v11/strumbelj10a.html

Recommendations

• How to explain individual classification decisions
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• Interpretable concept-based classification with Shapley values
• scientific article; zbMATH DE number 1934575
• A Symbolic Approach for Counterfactual Explanations

zbMATH Keywords

classificationvisualizationexplanationdata postprocessing

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Cooperative games (91A12)

Cited In (33)

• Non-linear dimension reduction in factor-augmented vector autoregressions
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• Counterfactual explanation of machine learning survival models
• Explanation with the winter value: efficient computation for hierarchical Choquet integrals
• The computational complexity of understanding binary classifier decisions
• Explanation with the Winter value: efficient computation for hierarchical Choquet integrals
• Foundations of fine-grained explainability
• On the failings of Shapley values for explainability
• A theory of dichotomous valuation with applications to variable selection
• Explaining predictive models using Shapley values and non-parametric vine copulas
• Variance reduced Shapley value estimation for trustworthy data valuation
• A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C
• Comments on ``Data science, big data and statistics
• Title not available (Why is that?)
• Title not available (Why is that?)
• Local interpretation of supervised learning models based on high dimensional model representation
• Improving regression predictions using individual point reliability estimates based on critical error scenarios
• A comparative study of methods for estimating model-agnostic Shapley value explanations
• A \(k\)-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning
• Interpretable concept-based classification with Shapley values
• An illustration of model agnostic explainability methods applied to environmental data
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Variable importance evaluation with personalized odds ratio for machine learning model interpretability with applications to electronic health records-based mortality prediction
• A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov-Smirnov bounds
• How to explain individual classification decisions
• Explanation of pseudo-Boolean functions using cooperative game theory and prime implicants
• Assessment of the influence of features on a classification problem: an application to COVID-19 patients
• Explaining machine learning models using entropic variable projection
• PredDiff: explanations and interactions from conditional expectations
• Necessary players and values
• Wasserstein-based fairness interpretability framework for machine learning models

This page was built for publication: An efficient explanation of individual classifications using game theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896017)