A \(k\)-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning

DOI10.1016/j.artint.2023.104014arXiv2211.02166OpenAlexW4386865177MaRDI QIDQ6067036

Guilherme Dean Pelegrina, Michel Grabisch, Leonardo Tomazeli Duarte

Publication date: 14 December 2023

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2211.02166

zbMATH Keywords

Choquet integralmachine learningShapley valueslocal interpretability

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Graph theory (including graph drawing) in computer science (68R10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Set functions, games and capacities in decision making
• Subjective evaluation of discomfort in sitting positions
• Monotonic solutions of cooperative games
• The application of fuzzy integrals in multicriteria decision making
• \(k\)-order additive discrete fuzzy measures and their representation
• Least angle regression. (With discussion)
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• The multilinear model in multicriteria decision making: the case of 2-additive capacities and contributions to parameter identification
• Explanation in artificial intelligence: insights from the social sciences
• A random forest guided tour
• Theory of capacities
• Alternative Representations of Discrete Fuzzy Measures for Decision Making
• A decade of application of the Choquet and Sugeno integrals in multi-criteria decision aid

This page was built for publication: A \(k\)-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning