Finding Regions of Counterfactual Explanations via Robust Optimization, İlker Birbil, University of Amsterdam

Counterfactual explanations play an important role in detecting bias and improving the explainability of data-driven classification models. A counterfactual explanation (CE) is a minimal perturbed data point for which the decision of the model changes. Most of the existing methods can only provide one CE, which may not be achievable for the user. In this work we derive an iterative method to calculate robust CEs, i.e., CEs that remain valid even after the features are slightly perturbed. To this end, our method provides a whole region of CEs allowing the user to choose a suitable recourse to obtain a desired outcome. We use algorithmic ideas from robust optimization and prove convergenc results for the most common machine learning methods including logistic regression, decision trees, random forests, and neural networks. Our experiments show that our method can efficiently generate globally optimal robust CEs for a variety of common data sets and classification models.

Short Bio

Ilker Birbil is a professor of AI & Optimization Techniques for Business & Society in University of Amsterdam, where he is the head of the Business Analytics Department. He had served for three years as a professor of Data Science and Optimization at the Department of Econometrics of Erasmus University, and before that he had been a professor of optimization at the Industrial Engineering Department of Sabancı University for more than a decade. His research interests center around optimization methods in data science and decision making. Lately, he is working on explainable artificial intelligence, optimization for machine learning, and data privacy in operations research.

Friday, November 24th, 2023, 4:00 pm

IE Building, Halim Doğrusöz Auditorium (Ground Floor-03)