In this talk I will present two recent examples of my research on explainability problems over machine learning (ML) models. In rough terms, these explainability problems deal with specific queries one poses over a ML model in order to obtain meaningful justifications for their results. Both of the examples I will present deal with “local” and “post-hoc” explainability queries. Here “local” means that we intend to explain the output of the ML model for a particular input, while “post-hoc” refers to the fact that the explanation is obtained after the model is trained. In the process I will also establish connections with problems studied in data management. This with the intention of suggesting new possibilities for cross-fertilization between the area and ML.
Speaker: Pablo Barceló.
Full Professor at Pontificia Universidad Católica de Chile, where he also acts as Director of the Institute for Mathematical and Computational Engineering. He is the author of more than 80 technical papers, has chaired ICDT 2019, will be chairing ACM PODS 2022, and is currently a member of the editorial committee of Logical Methods in Computer Science. From 2011 to 2014 he was the editor of the database theory column of SIGMOD Record. His areas of interest are database theory, logic in computer science, and the emerging relationship between these areas and machine learning.