Biosketch
Yuxin obtained her master degree from National University of Singapore majoring in Statistics after gained the bachelor degree from Beihang Universitiy, school of Mathematics.
Now she is a PhD candidate at the Institute of AI in Management, LMU Munich, under the supervision of Prof. Stefan Feuerriegel.
relAI Research
Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring
Dropout is common in clinical studies, with up to half of patients leaving early. When dropout is informative (i.e., dependent on survival time), it introduces censoring bias, causing treatment effect estimates to be biased. We propose an assumption-lean framework to assess the robustness of conditional average treatment effect (CATE) estimates in survival analysis under censoring bias. Unlike existing work that relies on non-informative censoring for point identification, we use partial identification to derive informative bounds on the CATE, helping identify patient subgroups where treatment remains effective despite informative censoring. We further propose a novel model-agnostic meta-learner, the \textbf{SurvB-learner}, to estimate these bounds, with favorable theoretical properties including double-robustness and quasi-oracle efficiency. We demonstrate the effectiveness of our approach across simulated and real-world experiments.