van der Schaar Lab

Causal deep learning: a new framework

Causality has the potential to truly transform the way we solve a large number of real-world problems. Yet, so far, its potential remains largely unlocked since most work so far requires strict assumptions which do not hold true in practice.

To address this challenge and make progress in solving real-world problems, we propose a new way of thinking about causality – we call this causal deep learning.

The framework which we propose for causal deep learning spans three dimensions: (1) a structural dimension, which allows incomplete causal knowledge rather than assuming either full or no causal knowledge; (2) a parametric dimension, which encompasses parametric forms which are typically ignored; and finally, (3) a temporal dimension, which explicitly allows for situations which capture exposure times or temporal structure.

Map of Causal Deep Learning

Together, these dimensions allow us to make progress on a variety of real-world problems by leveraging (sometimes incomplete) causal knowledge and/or combining diverse causal deep learning methods. This new framework also enables researchers to compare systematically across existing works as well as identify promising research areas which can lead to real-world impact.

Our map is proposed as a paper which you can read here: https://arxiv.org/abs/2303.02186. As CDL encompasses a community, we welcome discussion and suggestions.

We look forward to what the future of CDL holds!

Jeroen Berrevoets

Jeroen Berrevoets joined the van der Schaar Lab from the Vrije Universiteit Brussel (VUB). Prior to this, he analyzed traffic data at 4 of Belgium’s largest media outlets and performed structural dynamics analysis at BMW Group in Munich.

As a PhD student in the van der Schaar Lab, Jeroen plans to explore the potential of machine learning in aiding medical discovery, rather than simply applying it to non-obvious predictions. His main research interests involve using machine learning and causal inference to gain understanding of various diseases and medications.

Much of this draws from his firmly-held belief that, “while learning to predict, machine learning models captivate some of the underlying dynamics and structure of the problem. Exposing this structure in fields such as medicine, could prove groundbreaking for disease understanding, and consequentially drug discovery.”

Jeroen’s studentship is supported under the W. D. Armstrong Trust Fund. He will be supervised jointly by Mihaela van der Schaar and Dr. Eoin McKinney.

Mihaela van der Schaar

Mihaela van der Schaar is the John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge and a Fellow at The Alan Turing Institute in London.

Mihaela has received numerous awards, including the Oon Prize on Preventative Medicine from the University of Cambridge (2018), a National Science Foundation CAREER Award (2004), 3 IBM Faculty Awards, the IBM Exploratory Stream Analytics Innovation Award, the Philips Make a Difference Award and several best paper awards, including the IEEE Darlington Award.

In 2019, she was identified by National Endowment for Science, Technology and the Arts as the most-cited female AI researcher in the UK. She was also elected as a 2019 “Star in Computer Networking and Communications” by N²Women. Her research expertise span signal and image processing, communication networks, network science, multimedia, game theory, distributed systems, machine learning and AI.

Mihaela’s research focus is on machine learning, AI and operations research for healthcare and medicine.