Awesome

ECE: Ensemble of Counterfactual Explainers

Riccardo Guidotti, Salvatore Ruggieri
Department of Computer Science, University of Pisa, Italy
riccardo.guidotti@unipi.it, salvatore.ruggieri@unipi.it

In eXplainable Artificial Intelligence (XAI), several counterfactual explainers have been proposed, each focusing on some desirable properties of counterfactual instances: minimality, actionability, stability, diversity, plausibility, discriminative power. We propose an ensemble of counterfactual explainers that boosts weak explainers, which provide only a subset of such properties, to a powerful method covering all of them. The ensemble runs weak explainers on a sample of instances and of features, and it combines their results by exploiting a diversity-driven selection function. The method is model-agnostic and, through a wrapping approach based on autoencoders, it is also data-agnostic

References

[1] R. Guidotti, S. Ruggieri. Ensemble of Counterfactual Explainers. Discovery Science (DS 2021). 358-368. Vol. 12986 of LNCS, Springer, October 2021.