On the computation of counterfactual explanations -- A survey
This is an incremental survey that addresses the need for explainable AI by reviewing and extending methods for counterfactual explanations, relevant for practitioners and researchers in machine learning.
The paper surveys model-specific methods for efficiently computing counterfactual explanations of machine learning models and proposes new methods for previously unaddressed models, aiming to enhance interpretability in practical applications.
Due to the increasing use of machine learning in practice it becomes more and more important to be able to explain the prediction and behavior of machine learning models. An instance of explanations are counterfactual explanations which provide an intuitive and useful explanations of machine learning models. In this survey we review model-specific methods for efficiently computing counterfactual explanations of many different machine learning models and propose methods for models that have not been considered in literature so far.