On Shapley value interpretability in concept-based learning with formal concept analysis

DOI10.1007/S10472-022-09817-YMaRDI QIDQ2107486zbMATH OpenOpenAlexFDO

Authors Dmitry I. Ignatov, Léonard Kwuida

Publication date 1 December 2022

Published in Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10472-022-09817-y

zbMATH Keywords

Shapley valueclosed itemsetsformal conceptsrule-based learninginterpretable machine learningBanzhaf-Penrose index

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Galois correspondences, closure operators (in relation to ordered sets) (06A15) Complete lattices, completions (06B23)

Recommendations

• Interpretable concept-based classification with Shapley values
• On Shapley Value for Measuring Importance of Dependent Inputs
• Games on concept lattices: Shapley value and core
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• Machine learning on the basis of formal concept analysis

Cites work

• scientific article; zbMATH DE number 3823743 (Why is no real title available?)
• scientific article; zbMATH DE number 1249514 (Why is no real title available?)
• scientific article; zbMATH DE number 3078997 (Why is no real title available?)
• A note on limit results for the Penrose-Banzhaf index
• Algorithms for computing the Shapley value of cooperative games on lattices
• Approximating concept stability
• Boundary relations, graphs and collective solutions
• Concept Lattices
• Conceptual exploration
• Galois connections in data analysis: Contributions from the Soviet era and modern Russian research
• Games on concept lattices: Shapley value and core
• Interpretable concept-based classification with Shapley values
• Mathematical aspects of concept analysis
• On attribute reduction in concept lattices: methods based on discernibility matrix are outperformed by basic clarification and reduction
• On interestingness measures of formal concepts
• On stability of a formal concept
• On the complexity of calculating factorials
• Towards Concise Representation for Taxonomies of Epistemic Communities

Cited in

(3)

• On the number of maximal antichains in Boolean lattices for \(n\) up to 7
• Interpretable concept-based classification with Shapley values
• A \(k\)-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning

This page was built for publication: On Shapley value interpretability in concept-based learning with formal concept analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2107486)