Seminar: Ilker Birbil (Universiteit van Amsterdam)

Counterfactual explanations embody one of the many interpretability techniques that receive increasing attention from the machine learning community. Their potential to make model predictions more sensible to the user is considered to be invaluable. To increase their adoption in practice, several criteria that counterfactual explanations should adhere to have been put forward in the literature. We propose counterfactual explanations using optimization with constraint learning, a generic and flexible approach that addresses all these criteria and allows room for further extensions. Specifically, we discuss how we can leverage an optimization with constraint learning framework for the generation of counterfactual explanations, and how components of this framework readily map to the criteria. We also propose new novel modeling approaches to address data manifold closeness and diversity, which are two key criteria for practical counterfactual explanations. We test our approaches on several datasets and present our results in a case study. Compared to a current state-of-the-art method, our modeling approach has shown an overall superior performance in terms of several evaluation metrics proposed in related work while allowing more room for flexibility.

Video: