FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles

By Ana Lucic, Harrie Oosterhuis, Hinda Haned, Maarten de Rijke. 2019

95 citations recorded by the source corpus.

Model interpretability has become an important problem in machine learning (ML) due to the increased effect algorithmic decisions have on humans. Counterfactual explanations can help users understand not only why ML models make certain decisions, but also how these decisions can be changed. We frame the problem of finding counterfactual explanations as an optimization task and extend previous work that could only be applied to differentiable models. In order to accommodate non-differentiable models such as tree ensembles, we use probabilistic model approximations in the optimization framework. We introduce an approximation technique that is effective for finding counterfactual explanations for predictions of the original model and show that our counterfactual examples are significantly closer to the original instances than those produced by other methods specifically designed for tree ensembles.

Subfields: Artificial Intelligence

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

Citations in the corpus

Mathematical optimization in classification and regression trees (2021, background): “Instead, one can offer to individuals counterfactual explanations (Fernández et al. 2020; Lucic et al. 2020; Mothilal et al. 2020).”
Data-centric Artificial Intelligence: A Survey (2023, unknown): “White-box methods necessitate access to the evaluated models, which can be achieved through complete internals [36, 111, 138], gradients [225], or solely the prediction function [52, 57, 127, 202].”