LFCS Seminar: 27July 2021 - Leopoldo Bertossi

Title: Score-Based Explanations for Classification Results

Abstract:

We will present recent results on the use of score-based explanations for outcomes from classification models. The discussion will turn around the Responsibility and Shap scores that can be applied with black-box and open models. The emphasis will be on how the problem of score computation, that is in general intractable, can be made tractable when one has access to certain classes of classifiers.

Bio:

Leopoldo Bertossi has been Full Professor at the School of Computer Science, Carleton University (Ottawa, Canada) from 2001 to 2019, and Emeritus Professor from 2019 to date. He is a full-professor at Universidad Adolfo Ibañez (UAI, Chile), the oldest and most prestigious fully-private university in Chile.

He is a Senior Computer Scientist at RelationalAI Inc., since August 2018.

He is since 2019 a senior member of the "Millenium Research Institute for Foundations of Data" (IMFD, Chile), a 10-year initiative funded by the Government of Chile.

Until 2001 he was professor at the Department of Computer Science, School of Engineering of the Catholic University of Chile (PUC), and departmental chair (1993-1995). He was the President of the Chilean Computer Science Society (SCCC) in 1996 and 1999-2000.

He obtained a PhD in Mathematics from the Pontifical Catholic University of Chile (PUC) in 1988, with a PhD thesis on mathematical logic (model theory) under the supervision of Prof.

Joerg Flum (University of Freiburg, Germany).

He has been visiting professor and researcher at several universities, among them: University of Toronto (1989/90); Wisconsin-Milwaukee (1990/91); Marseille-Luminy (1997), Technical University Berlin (1997/98); Free University of Bolzano-Bozen, Italy (1995); University of Calabria (2014); Technical University of Vienna (2006 and 2017, as a Pauli Fellow of the "Wolfgang Pauli Institute (WPI) Vienna").

Prof. Bertossi's research interests include data science, database theory, data management, semantic web, intelligent information systems, data management for business intelligence, knowledge representation, uncertain reasoning, logic programming, computational logic, and statistical relational learning.