Doudou Zhou

About Me

I am an Assistant Professor of Statistics & Data Science at the National University of Singapore. I was a Postdoctoral Research Fellow in Biostatistics at Harvard University from 2022 to 2024, working with Prof. Tianxi Cai. I received a Ph.D in Statistics 2022 from the University of California, Davis (UC Davis), advised by Prof. Hao Chen. Before that, I received my B.S. in Statistics and B.E. in Computer Science (dual) from the University of Science and Technology of China (USTC) in 2019.

To Prospective Students:

I am seeking self-motivated students to join my research group or collaborate with me. If you are interested in collaborating, please email me your CV along with a brief introduction about yourself.

Research Interests

I am interested in developing statistical methodology and theory for electronic health records (EHR) data analysis. I’m also developing practical tools for analyzing high-dimensional and non-Euclidean data. I mainly work on representation learning, federated learning, transfer learning, reinforcement learning, network analysis, graph neural networks, large language models, and high-dimensional statistics. Recently, I am interested in:

• Multimodal and multi-institutional representation learning for data harmonization and knowledge graph integration.
• Federated reinforcement learning for precision medicine.
• Transfer learning of heterogeneous domains.
• Graph-based and rank-based methods for high-dimensional hypothesis testing.

Selected Awards

• 2023 Program in Quantitative Genomics Student/Postdoc Travel Award, Harvard
• 2022 ICSA Student Poster Award
• 2022 Student Paper Award, Statistical Learning and Data Science Section, ASA

Publications and Preprints

Statistical Methodology and Theory

• Cai, T.^#, Huang, F.^#, Nakada, R.^#, Zhang, L.^#, Zhou, D.^# Contrastive Learning on Multimodal Analysis of Electronic Health Records. (2024+) [arXiv]

• Liang, J.*, Liu, Y.*, Zhou, D., Zhang, S., Lu, J. The Wreaths of Coherence: Uniform Graph Feature Selection with False Discovery Rate Control. (2024+) [arXiv]

• Xu, Z., Gan, Z., Zhou, D., Shen, S., Lu, J., Cai, T. Inference of Dependency Knowledge Graph for Electronic Health Records. (2023+) [arXiv]

• Cai, T.^#, Xia, D.^#, Zhang, L.^#, Zhou, D.^# Consensus Knowledge Graph Learning via Multi-view Sparse Low Rank Block Model. (2023+) [arXiv]

• Zhou, D., Chen, H. RING-CPD: Asymptotic Distribution-free Change-point Detection for Multivariate and Non-Euclidean Data. (2022+) [arXiv]

• Zhou, D.*, Liu, M.*, Li, M., Cai, T. Doubly Robust Augmented Model Accuracy Transfer Inference with High Dimensional Features. Journal of the American Statistical Association: Theory and Methods, 2024. [arXiv]

• Zhou, D.*, Zhang, Y.*, Sonabend-W, A., Wang, Z., Lu, J., Cai, T. Federated Offline Reinforcement Learning. Journal of the American Statistical Association: Theory and Methods, 2024. [arXiv][code]

• Zhou, D., Cai, T., Lu, J. Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices. Journal of Machine Learning Research, 2023. [ code] [ package]

• Zhou, D., Chen, H. A New ranking Scheme for Modern Data and Its Application to Two-sample Hypothesis Testing. Conference on Learning Theory (COLT), 2023.

• Liu, M.^#, Zhang, Y.^#, Zhou, D.^# Double/Debiased Machine Learning for Logistic Partially Linear Model. The Econometrics Journal, 2021. [code]

Application

• Wen, J., et al. DOME: Directional Medical Embedding Vectors from Electronic Health Records.(2024+) [code]

• Gan, Z.*, Zhou, D.*, et al. ARCH: Large-scale Knowledge Graph via Aggregated Narrative Codified Health Records Analysis. (2023+) [medRxiv] [code] [ARCH APP]

• Yang, D., Zhou, D., Cai, S., Gan, Z., Pencina, M., Avillach, P., Cai, T., Hong, C. SONAR: Enabling Robust Automated Harmonization of Heterogeneous Data through Ensemble Machine Learning. (Under revision, 2023+) [preprint]

• Xiong, X., et al. Knowledge-Driven Online Multimodal Automated Phenotyping System. (2023+) [medRxiv] [KOMAP] [ONCE]

• Lou, Y., Chen, Y., Huang, Y., Zhou, D., Cao, Y., Wang, H. Two-stream Feature Extraction for Self-supervised Image Quality Assessment. IEEE International Conference on Data Mining (ICDM), 2023.

• Cai, B., Zeng, S., Lin, Y., Yuan, Z., Zhou, D., Tian, L. Hierarchical Pretraining for Biomedical Term Embeddings.Proceedings of the 18th Conference on Computational Intelligence Methods for Bioinformatics & Biostatistics (CIBB 2023).

• Wen, J., et. al. Multimodal Representation Learning for Predicting Molecule-Disease Relations. Bioinformatics, 2023.

• Zhou, D., et al. Multiview Incomplete Knowledge Graph Integration with Application to Cross-institutional EHR Data Harmonization. Journal of Biomedical Informatics, 2022. [MIKGI APP]

• Ahuja, Y., Liang, L., Zhou, D., Huang, S., Cai, T. Semisupervised Calibration of Risk with Noisy Event Times (SCORNET) using electronic health record data Biostatistics, 2022. [code]

• Hong, C., et al. Clinical Knowledge Extraction via Sparse Embedding Regression (KESER) with Multi-Center Large Scale Electronic Health Record Data. npj Digital Medicine, 2021. [KESER Network]

• Ahuja, Y., Zhou, D., He, Z., Sun, J., Castro, V., Gainer, V., Murphy, S., Hong, C., Cai, T. sureLDA: A Multidisease Automated Phenotyping Method for the Electronic Health Record. Journal of the American Medical Informatics Association, 2020. [code]

Services

Conference Reviewers

• AMIA Annual Symposium, 2020
• ACM MM, 2023
• NeurIPS, 2023

Journal Reviewers

• Journal of the American Statistical Association
• npj Digital Medicine
• Annals of Statistics
• Journal of Computational and Graphical Statistics
• Journal of Biomedical Informatics
• Knowledge and Information Systems