🗓️ Seminar MLG - April 17th 2025, 12AM
❓ Counterfactual Reasoning for Explainability and Fairness in Machine Learning
👨⚕️ Pr. Dimitris Sacharidis
📍 Campus de La Plaine - LIC.0.04: Learning Theatre
Abstract:
Counterfactual reasoning is a fundamental way we make sense of the world. Recently, several machine learning approaches have leveraged this mechanism to enhance the transparency of black-box models. The first part of the talk will focus on explainability, introducing counterfactual explanations and influence-based methods for understanding model behaviour. The second part will explore algorithmic fairness, explaining how counterfactuals are used to assess and audit fairness. It will also introduce the concept of algorithmic recourse and its connection to fairness.
About Dimitris Sacharidis:
Dimitris Sacharidis is an assistant professor at the Data Science and Engineering Lab of the Université Libre de Bruxelles. Prior to that he was an assistant professor at the Technical University of Vienna, and a Marie Skłodowska Curie fellow at the "Athena" Research Center and at the Hong Kong University of Science and Technology. He finished his PhD and undergraduate studies on Computer Engineering at the National Technical University of Athens, while in between he obtained an MSc in Computer Science from the University of Southern California. His research interests include data science, data engineering, and responsible AI. He has served as a PC member and has been involved in the organization of top related conferences, and has acted as a reviewer and editorial member of associated journals.