Shapley values for feature selection: The good, the bad, and the axioms.
Daniel Vidali FryerInga StrümkeHien D. NguyenPublished in: CoRR (2021)
Keyphrases
- feature selection
- machine learning
- axiomatic characterization
- feature set
- mutual information
- dimensionality reduction
- text categorization
- parameter values
- multi class
- cooperative
- text classification
- classification models
- model selection
- method for feature selection
- irrelevant features
- discriminative features
- standard deviation
- game theory
- first order logic
- classification accuracy
- support vector
- genetic algorithm