Causal Learning and Artificial Intelligence
Modern machine learning is still limited to a superficial description of reality that only holds when the experimental conditions are fixed. It largely ignores interventions in the world, domain shifts, and temporal structure. Locatello’s group focuses on learning causal representations and causal models from data to address these issues. Through rigorous theory and scalable algorithms, they enable AI agents to understand cause-and-effect relationships, the effect of interventions, and distribution changes underlying the data they encounter.
Advances in causal learning have promising applications in machine learning and artificial intelligence, including robustness, explainability, and fairness in recognition, reasoning, and planning tasks. Most importantly, their impact extends to discovering new scientific knowledge from massive amounts of data and serving as the interface between people and complex systems for decision-making.
Causal learning emerges by discovering structural knowledge about the data-generating process and meaningful abstractions that allow for well-defined causal relations. Research questions span theoretical identifiability and methodological innovations in causal learning, discovering objects and abstract entities, their factors of variations, and their causal relations. The group applies these methods to solve open problems in machine learning and enable new applications in the sciences.
Multiple PhD student and postdoc positions are available!
Prospective PhD students: please apply through https://phd.pages.ista.ac.at
Prospective postdoctoral fellows: please contact Francesco.Locatello@ista.ac.at
Causal discovery | Causal representation learning | Object discovery | Visual reasoning | Deep learning methods | AI for science
Lao D, Hu Z, Locatello F, Yang Y, Soatto S. 2024. Divided attention: Unsupervised multi-object discovery with contextually separated slots. 1st Conference on Parsimony and Learning. CPAL: Conference on Parsimony and Learning. View
Burg M, Wenzel F, Zietlow D, Horn M, Makansi O, Locatello F, Russell C. 2023. Image retrieval outperforms diffusion models on data augmentation. Journal of Machine Learning Research. View
Xu D, Yao D, Lachapelle S, Taslakian P, von Kügelgen J, Locatello F, Magliacane S. 2023. A sparsity principle for partially observable causal representation learning. Causal Representation Learning Workshop at NeurIPS 2023. CRL: Causal Representation Learning Workshop at NeurIPS, 54. View
ReX-Link: Francesco Locatello
Since 2023 Assistant Professor, Institute of Science and Technology Austria (ISTA)
2020 – 2023 Senior Applied Scientist, Amazon Web Services
2020 PhD, ETH Zurich (Max Planck – ETH Center for Learning Systems), Switzerland
2023 Hector Stiftung-Preis for outstanding scientific achievements in the field of Machine Learning
2022 ETH Silver Medal for outstanding doctoral dissertation
2019 Best Paper Award at the International Conference on Machine Learning (ICML)
2019 Google Ph.D. Fellowship in Machine Learning