Dutch Seminar on Optimization (online series) with Ilker Birbil (University of Amsterdam)

The Dutch Seminar on Optimization is an initiative to bring together researchers from the Netherlands and beyond, with topics that are centered around Optimization in a broad sense. We would like to invite all researchers, especially also PhD students, who are working on related topics to join the events.

The Dutch Seminar on Optimization is an initiative to bring together researchers from the Netherlands and beyond, with topics that are centered around Optimization in a broad sense. We would like to invite all researchers, especially also PhD students, who are working on related topics to join the events. We hereby announce the following talk, given by Ilker Birbil (University of Amsterdam):

Speaker: Ilker Birbil (University of Amsterdam)
Title: Counterfactual Explanations Using Optimization With Constraint Learning
Date: Thursday 25th August, 4pm CET

Abstract:
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.