Xiaobin Shen

Office 3002, Hamburg Hall

Carnegie Mellon University

4800 Forbes Ave

Pittsburgh, PA 15213

I am Xiaobin Shen, a PhD student in Information Systems & Management at Carnegie Mellon University’s Heinz College. My research focuses on building responsible and trustworthy machine learning models for practitioners, particularly in healthcare, with an emphasis on survival analysis and causal inference. I am very fortunate to be advised by George H. Chen.

Before my doctoral studies, I earned a Master of Information Systems Management (Business Intelligence & Data Analytics) from Carnegie Mellon University’s Heinz College, and a Bachelor of Management Sciences in Information Management and Information Systems from Zhejiang University School of Management.

A fun pattern across my academic path is the intersection of information systems (technology 💻) and management (people 👥) — happy to chat if you’re into that intersection too.

I am also proud to be a first-generation college student.

Selected Publications

ICLR

SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis

Shahriar Noroozizadeh^†, Xiaobin Shen^†, Jeremy Weiss, and George H. Chen

Accepted at International Conference on Learning Representations, Apr 2026

Abs HTML Code

Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as precision medicine and individualized policy-making. Yet, the survival analysis setting poses unique challenges for HTE estimation due to censoring, unobserved counterfactuals, and complex identification assumptions. Despite recent advances, from Causal Survival Forests to survival meta-learners and outcome imputation approaches, evaluation practices remain fragmented and inconsistent. We introduce SurvHTE-Bench, the first comprehensive benchmark for HTE estimation with censored outcomes. The benchmark spans (i) a modular suite of synthetic datasets with known ground truth, systematically varying causal assumptions and survival dynamics, (ii) semi-synthetic datasets that pair real-world covariates with simulated treatments and outcomes, and (iii) real-world datasets from a twin study (with known ground truth) and from an HIV clinical trial. Across synthetic, semi-synthetic, and real-world settings, we provide the first rigorous comparison of survival HTE methods under diverse conditions and realistic assumption violations. SurvHTE-Bench establishes a foundation for fair, reproducible, and extensible evaluation of causal survival methods.
ML4H

Deep Kernel Aalen-Johansen Estimator: An Interpretable and Flexible Neural Net Framework for Competing Risks

Xiaobin Shen^* and George H. Chen^*

Machine Learning for Health, Dec 2025

🏆 Best Paper Award (Models and Methods)

HTML Code
MLHC

Stepwise Fine and Gray: Subject-Specific Variable Selection Shows When Hemodynamic Data Improves Prognostication of Comatose Post-Cardiac Arrest Patients

Xiaobin Shen, Jonathan Elmer, and George H. Chen

Proceedings of the 10th Machine Learning for Healthcare Conference, Aug 2025

HTML Code
MLHC

Neurological Prognostication of Post-Cardiac-Arrest Coma Patients Using EEG Data: A Dynamic Survival Analysis Framework with Competing Risks

Xiaobin Shen, Jonathan Elmer, and George H Chen

Proceedings of the 8th Machine Learning for Healthcare Conference, Aug 2023

HTML Code