Ran Xu

Room N410, Mathematics and Science Center

400 Dowman Dr, Atlanta, GA 30307

My name is Ran Xu. I’m a 3rd year Ph.D. student in Department of Computer Science at Emory University, co-advised by Prof. Carl Yang and Prof. Joyce Ho. Before that, I obtained my bachelor’s degree (with Highest Honors) from the Department of Computer Science, Emory University in 2021, where I worked under the supervision of Prof. Jinho Choi.

My current research interest focuses on graph learning, natural language processing and their biomedical applications. Feel free to drop me an email (ran.xu at emory dot edu) if you have any questions about my research, or want to discuss about potential collaborations.

Educations

Emory University (2021 - Present)

Ph.D. in Computational Science and Informatics

GPA: 3.98/4.00

Research Focus: EHR modeling, Clinical NLP, Large Language Models.

Advisor: Prof. Carl Yang & Prof. Joyce Ho

Emory University (2017 - 2021)

B.S. in Computer Science, Double Major in Applied Mathematics

GPA: 3.97/4.00

Research Focus: Natural Language Processing.

Advisor: Prof. Jinho Choi

Industrial Experience

Meta Platforms, Inc. (May 2020 - Aug 2020): Enterprise Engineer Intern; Mentor: Zexi Zhang

News

Apr 6, 2023	One short paper on weakly supervised scientific document classification is accepted to SIGIR 2023.
Nov 28, 2022	Our paper Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR received the Best Paper Award (2 in total) at the Machine Learning for Health 2022.
Nov 19, 2022	One paper on Few-shot Learning for Language Models is accepted to AAAI 2023 as Oral presenation.

Selected Publications

Weakly-supervised Scientific Document Classification via Retrieval-Augmented Multi-stage Training

Ran Xu*, Yue Yu*, Joyce C Ho, and Carl Yang

Proceedings of SIGIR, 2023.

arXiv Code
Neighborhood-regularized Self-Training for Learning with Few Labels

Ran Xu, Yue Yu, Hejie Cui, Xuan Kan, Yanqiao Zhu, Joyce Ho, Chao Zhang, and Carl Yang

Proceedings of AAAI, 2023. (Oral)

arXiv PDF Code
Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR

Ran Xu, Yue Yu, Chao Zhang, Mohammed K Ali, Joyce C Ho, and Carl Yang

Proceedings of ML4H, 2022. (Best Paper Award)

Abs PDF Code

Electronic Health Record modeling is crucial for digital medicine. However, existing models ignore higher-order interactions among medical codes and their causal relations towards downstream clinical predictions. To address such limitations, we propose a novel framework CACHE, to provide effective and insightful clinical predictions based on hypergraph representation learning and counterfactual and factual reasoning techniques. Experiments on two real EHR datasets show the superior performance of CACHE. Case studies with a domain expert illustrate a preferred capability of CACHE in generating clinically meaningful interpretations towards the correct predictions.