Random forest explainability using counterfactual sets

By Rubén R. Fernández, Isaac Martín de Diego, Víctor Aceña, Alberto Fernández-Isabel, Javier M. Moguerza. 2020

79 citations recorded by the source corpus.

Abstract Nowadays, Machine Learning (ML) models are becoming ubiquitous in today’s society, supporting people with their day-to-day decisions. In this context, Explainable ML is a field of Artificial Intelligence (AI) that focuses on making predictive models and their decisions interpretable by humans, enabling people to trust predictive models and to understand the underlying processes. A counterfactual is an effective type of Explainable ML technique that explains predictions by describing the changes needed in a sample to flip the outcome of the prediction. In this paper, we introduce counterfactual sets, an explanation approach that uses a set of counterfactuals to explain a prediction rather than a single counterfactual, by defining a sub-region of the feature space where the counterfactual holds. A method to extract counterfactual sets from a Random Forest (RF), the R a n d o m F o r e s t O p t i m a l C o u n t e r f a c t u a l S e t E x t r a c t o r ( R F − O C S E ) , is presented. The method is based on a partial fusion of tree predictors from a RF into a single Decision Tree (DT) using a modification of the CART algorithm, and it obtains a counterfactual set that contains the optimal counterfactual. The proposal is validated through several experiments against existing alternatives on ten well-known datasets by comparing the percentage of valid counterfactuals, distance to the factual sample, and counterfactual sets quality.

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

Counterfactual Explanations for Machine Learning: A Review (2020, methodology): “As examples, gradient based algorithms can only handle differentiable models, the algorithms based on solvers require linear or piece-wise linear models [95, 107, 64, 65, 63], some algorithms are model-speciﬁc and only work for those models like tree ensembles [104, 63, 47, 79].”
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, background): “Fernández et al. introduce the notion of counterfactual sets to enhance counterfactual diversity [81].”
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review (2020, unknown): “Access to the complete model internals is required when the algorithm uses a solver-based method like, mixed integer programming [179, 182, 183, 287, 331] or if they operate on decision trees [52, 110, 222, 241, 323] which requires access to all internal nodes of the tree.”
Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI (2021, background): “Recent work has shown how to efficiently reduce a DF to a single decision tree [90,91] from which counterfactuals can be easily observed by the leaf nodes, so it could be used as a model for global explanations (see Fig.”