09.06.2024
Counterfactual explanations (CEs) are advocated as being ideally suited to providing algorithmic recourse for subjects affected by the predictions of machine learning models. While CEs can be beneficial to affected individuals, recent work has exposed severe issues related to the robustness of state-of-the-art methods for obtaining CEs. Since a lack of robustness may compromise the validity of CEs, techniques to mitigate this risk are in order. In this talk we will begin by introducing the problem of (lack of) robustness, discuss its implications and present some recent solutions we developed to compute CEs with robustness guarantees.
Francesco Leofante is a researcher affiliated with the Centre for Explainable AI at Imperial College in London. His main research areas are safe and explainable AI, with special emphasis on contrastive explanations and their robustness. He obtained a PhD in Computer Science from RWTH Aachen University and UNIGE with a thesis on AI Planning.
Join us for his talk and a discussion afterwards!