The van der Schaar Lab’s twelfth Inspiration Exchange session took place virtually on November 3, 2021, and was attended by students and professionals from the AI and machine learning community.
This session revisited the crucial topic of individualized treatment effect (ITE) inference, with a particular focus on looking to the future and introducing and discussing some brand-new approaches.
The first half of the session featured short presentations given by Ph.D. students Alicia Curth and Zhaozhi Qian. The latter half of the session featured a Q&A, in which Mihaela, Alicia, and Zhaozhi answered questions from audience members about their research and individualized treatment effects in general.
Introduction – 0:00
Announcement regarding Ph.D. student recruitment – 3:21
Announcement regarding 2021 open house videos – 4:21
Welcome message from Mihaela van der Schaar – 5:37
Presentation 1 by Alicia Curth [inductive biases for heterogeneous treatment effect estimation] – 7:42
Presentation 2 by Alicia Curth [learning heterogeneous treatment effects from time-to-event data] – 17:01
Presentation by Zhaozhi Qian [treatment effect estimation with longitudinal outcomes] – 28:22
Presentation by Zhaozhi Qian [estimating multi-cause treatment effects via single-cause perturbation] – 36:26
Q&A question 1 [data reliability for causal inference] – 46:19
Q&A question 2 [validation for clinical implementation of models] – 50:07
Q&A question 3 [metrics and methods for feature engineering] – 54:44
Q&A question 4 [feature importance for treatment response] – 57:06
Intro to next sessions – 59:13
A full list of the lab’s publications can be found here.