The Web Conference 2020,“Health on the Web” track

Causality and inductive bias for stability, robustness, and generalization & Detecting failure modes of machine learning systems Description: As machine learning models start to be more widely used in clinical practice, their robustness and reliability become critical. However, it is widely known that such models can be brittle and significantly underperform when deployed in environments with distribution shifts from the training datasets. The research roundtable explored ways of determining when models may fail to generalize in practice and highlight how principles from causality can be used to improve the reliability of such machine learning models in the healthcare setting.
Senior chairs: Adarsh Subbaswamy, Wojciech Samek, Federico Cabitza, Lukas Ruff
Junior chairs: Utkarshani Jaimini,Kaushik Manjunatha, Golam Rasul