Explanations of model predictions with live and breakDown packages
By Mateusz Staniak, Przemyslaw Biecek. 2018
147 citations recorded by the source corpus.
Complex models are commonly used in predictive modeling. In this paper we present R packages that can be used to explain predictions from complex black box models and attribute parts of these predictions to input features. We introduce two new approaches and corresponding packages for such attribution, namely live and breakDown. We also compare their results with existing implementations of state of the art solutions, namely lime that implements Locally Interpretable Model-agnostic Explanations and ShapleyR that implements Shapley values.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Alicja Gosiewska
- Przemyslaw Biecek
- D. V. Carvalho
- Eduardo Marques Pereira
- Jaime S. Cardoso
- Q. Liao
- Anders Søgaard
- Karthikeyan K
In Computer Vision and Pattern Recognition
In Safety, Robustness & Interpretability
In Human-Computer Interaction
Citations in the corpus
- Do Not Trust Additive Explanations (2019, methodology): “Another local method is Break Down (Staniak and Biecek, 2018).”
- Machine Learning Interpretability: A Survey on Methods and Metrics (2019, background): “Partial Dependence Plot [142] Global Feature summary Individual Condition Expectation [143] Global/Local Feature summary Accumulated Local Effects Plot [144] Global Feature summary Feature Interaction [145] Global Feature summary Feature Importance [146] Global/Local Feature summary Local Surrogate ”