10 papers
SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths
Timo HeiÃ, Julia Herbinger, Bernd Bischl +1
Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their f…
Analyzing Error Sources in Global Feature Effect Estimation
Timo HeiÃ, Coco Bögel, Bernd Bischl +1
Global feature effects such as partial dependence (PD) and accumulated local effects (ALE) plots are widely used to interpret black-box models. However, they are only estimates of…
CASHomon Sets: Efficient Rashomon Sets Across Multiple Model Classes and their Hyperparameters
Fiona Katharina Ewald, Martin Binder, Matthias Feurer +2
Rashomon sets are model sets within one model class that perform nearly as well as a reference model from the same model class. They reveal the existence of alternative well-perfor…
xplainfi: Feature Importance and Statistical Inference for Machine Learning in R
Lukas Burk, Fiona Katharina Ewald, Giuseppe Casalicchio +2
We introduce xplainfi, an R package built on top of the mlr3 ecosystem for global, loss-based feature importance methods for machine learning models. Various feature importance met…
Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
Vasilis Gkolemis, Loukas Kavouras, Dimitrios Kyriakopoulos +5
Generalized additive models (GAMs) offer interpretability through independent univariate feature effects but underfit when interactions are present in data. GAMs add selected p…
Optimal Transport Group Counterfactual Explanations
Enrique Valero-Leal, Bernd Bischl, Pedro Larrañaga +2
Group counterfactual explanations find a set of counterfactual instances to explain a group of input instances contrastively. However, existing methods either (i) optimize counterf…