Keynote Talk
"Querying Explanations: Declarative Languages for Explainable AI"
Abstract: Many different notions have been proposed to explain why a machine learning model makes a particular prediction. In this talk, I will present ExplAIner, a declarative query language that provides a unified framework for expressing and combining such explanation notions. ExplAIner can capture several important forms of explanations, including abductive, contrastive, feature-based, and distance-based explanations. I will discuss how this language connects ideas from explainable AI, databases, logic, and computational complexity. I will also show how our complexity results lead to practical algorithms based on SAT solvers, providing a general approach for computing explanations for different classes of machine learning models.
Biography
Marcelo Arenas is a Professor in the Department of Computer Science and the Institute for Mathematical and Computational Engineering at Pontificia Universidad Católica de Chile. He is an ACM Fellow and a former director of the Millennium Institute for Foundational Research on Data and the Center for Semantic Web Research. He received his Ph.D. in Computer Science from the University of Toronto in 2005. His research interests include data management, applications of logic in computer science, and explainable artificial intelligence. His research has received several distinctions, including an IBM Ph.D. Fellowship, a SIGMOD Jim Gray Doctoral Dissertation Award Honorable Mention, the Semantic Web Science Association Ten-Year Award, an ACM SIGMOD Research Highlight Award, and nine best paper awards at major conferences. He has also served on numerous program committees and editorial boards and has participated as an invited expert in the W3C and the OECD.