The VII AMMCS International Conference
Waterloo, Ontario, Canada | August 17-21, 2026
AMMCS 2026 Plenary Speaker
Computing Attribution Scores for Classification in Explainable AI
Dr. Leopoldo Bertossi
Attribution scores are used in XAI to quantitatively measure the strength of explanations for results from Machine Learning models. Several scores have been proposed and investigated. In addition to describing a few of them, including the popular SHAP-score, we will concentrate on the computational challenges they offer. Depending on the classifiers, some hardness and tractability results will be presented, so as an application with neural networks as classifiers.
Professor Leopoldo Bertossi is an Emeritus Professor of Computer Science at Carleton University, Canada; and an Adjunct Professor at Western University, London, Canada. He is a Senior Researcher at the Millennium Institute of Foundational Research on Data (IMFD, Chile). He has a PhD in Mathematics from the Catholic University of Chile (PUC, Chile). His areas of research are Explainable AI, Knowledge Representation, Data Management, and Computational Logic. Web page: https://people.scs.carleton.ca/~bertossi/.