From contrastive to abductive explanations and back again

Explanations of Machine Learning (ML) models often address a question. Such explanations can be related with selecting feature-value pairs which are sufficient for the prediction. Recent work has investigated explanations that address a question, i.e. finding a change of feature values that guarantee a change of prediction. Given their goals, these two forms of explaining predictions of ML models appear to be mostly unrelated. However, this paper demonstrates otherwise, and establishes a rigorous formal relationship between and explanations. Concretely, the paper proves that, for any given instance, explanations are minimal hitting sets of explanations and vice-versa. Furthermore, the paper devises novel algorithms for extracting and enumerating both forms of explanations.