van der Schaar Lab

Inspiration Exchange: ICML 2022 Preview

The van der Schaar Lab’s nineteenth Inspiration Exchange session took place on June 21, 2022. We had an especially interactive and engaging session. The session previewed the van der Schaar Lab’s accepted publications at the upcoming ICML 2022 conference and featured a roundtable discussion with industry guests, lively Q&A, and discussions. 

The session was a medley of presentations highlighting our 7 accepted papers, highlighting our lab’s continuing and impactful research. Our research encompasses a diverse array of topics, including discovering diverse classes of differential equations from data, machine learning interpretability, synthetic data, data-centric AI, AutoML, individualised treatment effects, and, last but not least, augmenting human skills using machine learning.

The presented research encompassed a diverse array of topics:

  • Nabeel Seedat (PhD student) presented Data-Suite, a data-centric framework to identify incongruous regions of in-distribution data,
  • Alicia Curth (PhD student)presented HyperImpute, an imputation method that marries the advantage of iterative imputation and deep generative modelling to adaptively and automatically configure imputation models,
  • Prof Mihaela van der Shaar briefly presented a domain- and model-agnostic evaluation metric for generative models,
  • Samuel Holt  (PhD student) introduced Neural Laplace, a unified framework for learning diverse classes of differential equations in the Laplace domain,
  • Dr Fergus Imrie (Postdoc) presented TE-CDE, which estimates counterfactual outcomes in continuous time using neural controlled differential equations,
  • Jonathan Crabbé (PhD student) presented a method to interpret unsupervised models, introducing post-hoc, label-free feature importance and label-free example importance explanations,
  • Alihan Hüyük (PhD student) discussed his work on inverse contextual bandits, which offers a quantitative and interpretable account of how clinical practice has evolved over time.

We then held our roundtable discussion, where our industry guests Dr Ari Ercole (University of Cambridge) and Dr Razvan Pascanu (DeepMind) shared their perspectives on ML and the medical impacts of the presented works. The session was then opened up to the audience for Q&A and general discussion

We encourage you to learn more about the presented work by reading the described papers. The titles, authors, abstract, and perceived impacts of all 7 papers can be found on our lab website

Inspiration Exchange – ICML 2022 Preview

Sign up for our upcoming sessions: https://www.vanderschaar-lab.com/engagement-sessions/inspiration-exchange/#

The lab’s publications are here: https://www.vanderschaar-lab.com/publications/

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.