PredDiff: explanations and interactions from conditional expectations

DOI10.1016/J.ARTINT.2022.103774OpenAlexW3133523710MaRDI QIDQ2093377

Stefan Blücher, Nils Strodthoff, Johanna Vielhaben

Publication date: 8 November 2022

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

Full work available at URL: https://arxiv.org/abs/2102.13519

zbMATH Keywords

interactionsinterpretabilityShapley valuesexplainable AIfeature attribution

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• Axiomatic characterizations of probabilistic and cardinal-probabilistic interaction indices
• On decompositions of multivariate functions
• Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models

This page was built for publication: PredDiff: explanations and interactions from conditional expectations