The 40th edition of the Conference on Uncertainty in Artificial Intelligence (UAI) took place between 15 and 19 July on the Ciutadella campus of Pompeu Fabra University, with the participation of experts from all over the world. It is one of the main international meetings on research related to the representation, learning and reasoning of knowledge in the presence of uncertainty.

UAI 2024 was organized by the Barcelona School of Economics (BSE), together with the UPF Departments of Engineering and Medicine and Life Sciences (MELIS), and with the support of the Association for Uncertainty in Artificial Intelligence (AUAI). Vicenç Gómez, a member Artificial Intelligence and Machine Learning Research Group of the Department of Engineering, and Roberto Castelo, a professor of Bioinformatics and Biostatistics and head of the Functional Genomics Research Group MELIS, sat on the local organizing committee.

It is one of the main international meetings on research related to the representation, learning and reasoning of knowledge in the presence of uncertainty

The three main presentations were given, respectively, by Nicolò Cesa-Bianchi, a professor at the University of Milan and Polytechnic University of Milan (Italy), with the title “The power of cooperation in networks of learning agents”; Dominki Janzing (Amazon Research Group), who gave the talk “All causal DAGs are but wrong some are useful”, and Vanessa Didelez (Leibniz Institute for Prevention Research and Epidemiology - BIPS) in Bremen, Germany, with “Between theory and praxis: causal inference & discovery in Epidemiology”.

The oral sessions covered topics such as probabilistic circuits for causal inference, causal representation learning, causal discovery, the role of causality in management, deep learning, cooperation in networks of learning agents, quantification of uncertainty, and optimization, equity, interpretability, and reproducibility in machine learning. Regarding the workshops, they were divided into three areas: tractable probabilistic modelling, causal inference and causal inference for time series data.

The Association for Uncertainty in Artificial Intelligence (AUAI) is a non-profit organization that focuses on organizing this annual conference, which has been held since 1985, and more generally, on promoting the search for advances in the representation of knowledge, learning and reasoning about uncertainty.