Seminar by Prof. Kun ZHANG from Department of Machine Learning, Carnegie Mellon University & Mohamed bin Zayed University of Artificial Intelligence

Causality is a fundamental notion in science, engineering, and even in machine learning. Uncovering the causal process behind observed data can naturally help answer 'why' and 'how' questions, inform optimal decisions, and achieve adaptive prediction. In many scenarios, observed variables (such as image pixels and questionnaire results) are often reflections of the underlying causal variables instead of causal variables themselves. Causal representation learning aims to reveal the underlying hidden causal variables and their relations. It can be seen as a special case of causal discovery, whose goal is to recover the underlying causal structure or causal model from observational data. The modularity property of a causal system implies properties of minimal changes and independent changes of causal representations, and in this talk, we show how such properties make it possible to recover the underlying causal representations from observational data with identifiability guarantees: under appropriate assumptions, the learned representations are consistent with the underlying causal process. Various problem settings are considered, involving independent and identically distributed (i.i.d.) data, temporal data, or data with distribution shift as input. We demonstrate when identifiable causal representation learning can benefit from flexible deep learning and when suitable parametric assumptions have to be imposed on the causal process, complemented with various examples and applications.

Kun Zhang is a professor and the acting chair of the machine learning department and the director of the Center for Integrative AI (CIAI) at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). He is also an associate professor of philosophy and an affiliate faculty in the machine learning department at Carnegie Mellon University (CMU). He has been actively developing methods for learning causality from all kinds of data, investigating machine learning problems including transfer learning, representation learning, and reinforcement learning from a causal perspective, and making use of causal approaches to address various problems in AI, healthcare, psychology, and biology. He has been frequently serving as a senior area chair, area chair, or senior program committee member for major conferences in machine learning or artificial intelligence, including UAI, NeurIPS, ICML, IJCAI, AISTATS, and ICLR. He was a co-founder and General & Program Co-Chair of the first Conference on Causal Learning and Reasoning (CLeaR 2022), a Program Co-Chair of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022), and a General Co-Chair of UAI 2023, and is a Program Co-Chair of IEEE International Conference on Data Mining (ICDM) 2024. He received the Best Student Paper Award at UAI 2010, a Best Paper Runner-up Award at CVPR 2019, the Test of Time Award Honorable Mention at International Conference on Machine Learning (ICML) 2022, and the Best Paper award at CLeaR 2024.