Guest Seminar: Ali Tajer

Ali Tajer

Professor of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute

Causal Representation Learning

Abstract: Machine learning (ML) has shown great success in learning low-dimensional and semantically interpretable representations of high-dimensional data. Recent leaps in designing transformers have further proliferated representation learning. Despite such success, strong generalization — transfer of the learned representations to new problems — is still an unsolved problem. Addressing strong representation requires moving away from learning good enough representations to learning ground truth representation. As a key step toward strong generalization, causal representation learning (CRL) has emerged as a cutting-edge field that merges the strengths of statistical inference, machine learning, and causal inference. Its objective is to estimate the ground truth latent representation of the data and the rich structures that model the interactions among the variables in the latent space.

In this talk, we will explore the latest advancements in the emerging field of CRL. We will introduce the foundational concepts and motivations behind combining representation learning with causal inference. Following a brief history of CRL, we will describe its primary objectives and the theoretical challenges. We will then review the key approaches to address these challenges, including CRL with multi-view observations, CRL with interventions on latent variables, and CRL applied to temporal data. We will also highlight real-world application opportunities, discuss the challenges in scaling CRL to practical use cases, and discuss open questions for CRL related to theoretical and empirical viewpoints.