The Statistical Methods for Health Equity Series is a monthly online series co-hosted by the Data Science for Health Equity community, the Alan Turing Institute Health Equity Interest Group, and the Department of Statistical Science at University College London.

---

We are excited to announce the next instalment of our webinar series with speaker Charles Jones from Imperial College London.

Specific details on the topic are as below:

Topic: 

Rethinking Fair Representation Learning for Performance-Sensitive Tasks

Abstract:

We will cover Charles' most recent preprint, "Rethinking Fair Representation Learning for Performance-Sensitive Tasks", which investigates the validity of prominent fairness methods when applied in settings such as medical imaging. The talk will provide an organising perspective on the fairness literature and demonstrate how to use causal reasoning to define and formalise different sources of dataset bias. Using this understanding, we will present fundamental limitations on fair representation learning when evaluation data is drawn from the same distribution as training data. We will further provide two hypotheses for the potential validity of these methods under distribution shift and present experimental evidence in their favour. The results explain apparent contradictions in the existing literature and reveal how rarely considered causal and statistical aspects of the underlying data affect the validity of fair representation learning. Preprint: https://arxiv.org/abs/2410.04120

Speaker Biography:

Charles Jones is a fourth-year PhD student at Imperial College London, advised by Professor Ben Glocker. Charles' research is at the intersection of fairness and causality in machine learning for medical imaging. He is interested in how causality may be used as a unifying language to understand (and begin to solve) core problems in machine learning, such as fairness, robustness, and distribution shift. Charles' previous publications aim to illuminate lesser-known causal and statistical issues in the field of fairness in medical imaging. Moving forward, he is developing causal deep learning methods for mitigating such issues.

Website: https://charl-ai.github.io/

Scholar: https://scholar.google.com/citations?user=4PLajkUAAAAJ&hl=en

LinkedIn: https://www.linkedin.com/in/charles-jones1917/

--

Please direct any questions about the webinar series to Dr Brieuc Lehmann at b.lehmann@ucl.ac.uk.