van der Schaar Lab

Inspiration Exchange: Causal Deep Learning Part 2

The van der Schaar Lab’s eighteenth Inspiration Exchange session took place on May 27, 2022. We had an especially interactive and engaging session, with more than 80 participants joining the session live!

The session was a part 2 discussion on “Causal deep learning” and featured a roundtable discussion with industry guests, lively Q&A, and discussions. 

To start the session, Ph.D. student Jeroen Berrevoets discussed how Causal Deep Learning (Causal DL) can form a bridge between the world of causality, which is powerful and principled but often requires unrealistic assumptions, and that of deep learning. Subsequently, Jeroen presented several concrete examples of Causal DL, which showed improved regularisation, generalisation, imputation, and much more. Subsequently, Ph.D. student Boris van Breugel introduced a method to adapt causality principles in generating fair synthetic data.

We then held our roundtable discussion, where our industry guests Amit Sharma (Microsoft Research), Cheng Zhang (Microsoft Research), and Jim Weatherall (AstraZeneca) shared their perspectives on practical challenges that can be addressed through causal deep learning. The session was then opened up to the audience for Q&A and general discussion.

While Causal DL is still in its infancy, we believe that this research area will unlock the full potential of causality and catalyse important real-world impact in numerous domains, including our lab’s area of interest – medicine and healthcare.

If you’d like to learn more about causal deep learning, try taking a look at this recently published research pillar on our lab website. Additionally, you can find the part 1 discussion on causal deep learning here, and the part 2 discussion (most recent Inspiration Exchange) here

Inspiration Exchange – Causal Deep Learning Part 2

See our newly published research pillar here for more on this topic:

Sign up for our upcoming sessions:

The lab’s publications are here:

Nabeel Seedat

Before joining the van der Schaar Lab, Nabeel received a merit scholarship for a master’s degree at Cornell University, researching Bayesian deep learning and uncertainty estimation for high stakes applications. In addition, he holds a master’s degree from the University of the Witwatersrand (South Africa), where he was awarded a National Research Foundation grant for his work applying signal processing and machine learning to Parkinson’s disease diagnostics in low-resource settings.

Professionally, Nabeel has worked as a machine learning engineer in the United States and South Africa. The computer vision and natural language processing models he worked on are currently deployed and serving millions of customers on a daily basis.

Nabeel is keenly aware that taking methods from the lab to the bedside “requires a unique focus beyond just high-performance predictive models; it requires the development of a toolkit of methods for transfer learning across domains and locations, learning on smaller datasets, understanding model biases and quantifying model reliability and uncertainty are fundamentally needed to bridge this divide.”

Nabeel’s research is supported by funding from the Cystic Fibrosis Trust.