A k-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning.
Guilherme Dean PelegrinaLeonardo Tomazeli DuarteMichel GrabischPublished in: CoRR (2022)
Keyphrases
- choquet integral
- machine learning
- fuzzy measures
- aggregation operators
- nonlinear models
- pattern recognition
- data mining
- feature selection
- decision trees
- knowledge representation
- artificial intelligence
- decision making
- computational intelligence
- multi dimensional
- regression model
- attribute values
- statistical methods
- probability theory