On the Tractability of SHAP Explanations

DOI10.1613/jair.1.13283OpenAlexW3175110185MaRDI QIDQ5094036

Maximilian Schleich, Guy Van den Broeck, Dan Suciu, Anton Lykov

Publication date: 2 August 2022

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

Full work available at URL: https://arxiv.org/abs/2009.08634

zbMATH Keywords

machine learning

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Related Items (3)

Using analogical proportions for explanations ⋮ Explaining robust classification through prime implicants ⋮ Score-based explanations in data management and machine learning: an answer-set programming approach to counterfactual analysis

Uses Software

• shap

Cites Work

• Unnamed Item
• Unnamed Item
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• On probabilistic inference by weighted model counting
• The Complexity of Counting Cuts and of Computing the Probability that a Graph is Connected
• A Tractable and Expressive Class of Marginal Contribution Nets and Its Applications
• Graph-Based Algorithms for Boolean Function Manipulation
• Treewidth in Verification: Local vs. Global
• Theory and Applications of Satisfiability Testing

This page was built for publication: On the Tractability of SHAP Explanations