Francesco Locatello has been Assistant Professor at the Institute of Science and Technology Austria (ISTA) since 2023. Before joining ISTA, he worked as a Senior Applied Scientist at Amazon Web Services from 2021 to 2023. He completed his PhD at ETH Zurich and the Max Planck Institute for Intelligent Systems, supervised by Gunnar Rätsch and Bernhard Schölkopf. Locatello's research focuses on causality and AI. He has received several awards, including the Google Research Scholar Award in 2024, the Hector Stiftung-Preis in 2023, the ETH Silver Medal in 2022, and the Best Paper Award at ICML and Google PhD fellowship in 2019.
Francesco Locatello - Google Scholar Profile
Title and abstract of his presentation:
Causal Representation Learning for Science
Machine learning and AI have the potential to transform data-driven scientific discovery, enabling accurate predictions for several scientific phenomena. Much of the current progress is driven by scale, and conveniently, many scientific questions require analyzing massive amounts of data. At the same time, in scientific applications, predictions are often incorporated into broader analyses to draw new insights that are causal in nature. In this talk, I will discuss the open challenges of solving real-world causal downstream tasks in the sciences. Toward this, I will present a new framework for causal representation learning based on the invariance principle that generalizes most existing methodologies. With the increased flexibility, we show improved performance on our ISTAnt data set, the first real-world benchmark for estimating causal effects from high-dimensional observations in experimental ecology. Next, I will discuss contrastive and decoder-based causal representation learning methods and our efforts to scale them to real-world climate data. I will connect causal representation learning with recent advances in dynamical systems discovery that, when combined, enable learning scalable and controllable models with identifiable trajectory-specific parameters.
Thursday, October 3, 2024 at 4:00 p.m. // Währinger Straße 29, 2.OG, Hörsaal 2