I am Young-geun Kim, a postdoc fellow at the Department of Biostatistics and the Department of Psychiatry at Columbia University (Mentor: Ying Liu). I received a Ph.D. degree in Statistics from Seoul National University (Advisor: Myunghee Cho Paik), in 2021.

I am a data scientist with expertise in advanced techniques for biomedical data and their dissemination for medical research. My research topics include, but are not limited to:

• Deep generative models for multi-modal biomedical data (e.g., neuroimaging and multi-omics)
• Deep learning for identifying biomarkers associated with mental illness
• Reinforcement learning-based health care

Recent News

• [04-26-2024] Our work has been accepted at Frontiers in Psychiatry; Title: Explaining deep learning-based representations of resting state functional connectivity data: focusing on interpreting nonlinear patterns in autism spectrum disorder
• [01-29-2024] Our Invited Session proposal has been accepted by 2024 International Chinese Statistical Association (ICSA) (role: Speaker); Title: Recent Advances in Precision Medicine and Adaptive Experiments
• [01-19-2024] Our work has been selected as a poster presentation at the Adolescent Brain Cognitive Development (ABCD) Insights & Innovations Meeting hosted by ABCD Study’s federal collaborators; Title: Explaining Nonlinear Patterns in Children’s Structural MRI with Multi-modal Identifiable VAE
• [12-15-2023] I have been honored with the Career Development Award by the Korean International Statistical Society.

Selected Publications

1. Kim, Y.-G., Lee, K., and Paik, M.C. (2022). Conditional Wasserstein generator. IEEE Transactions on Pattern Analysis and Machine Intelligence. [Paper][Code]

2. Kim, Y.-G., Kwon, Y., and Paik, M.C. (2019). Valid oversampling schemes to handle imbalance. Pattern Recognition Letters, 125 (1): 661-667. [Paper] [Code]

3. Kim, Y.-G., Liu, Y., and Wei, X. (2023). Covariate-informed representation learning to prevent posterior collapse of iVAE. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2023). [Paper] [Code]

4. Kim, Y.-G., Kwon, Y., Chang, H., and Paik, M.C. (2020). Lipschitz continuous autoencoders in application to anomaly detection. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2020). [Paper] [Code]

Other Professional Activities

Conference Organizer

• (Accepted) Invited Session at Joint Statistical Meetings 2024 (role: Organizer & Speaker); Title: Reliable and Cost-effective Mental Health Care with Reinforcement Learning

• (Accepted) Invited Session at 2024 International Chinese Statistical Association (role: Speaker); Title: Recent Advances in Precision Medicine and Adaptive Experiments

• Invited Session at Eastern North American Region 2023 (role: Chair); Title: Advanced Methods for Analyzing Large-Scale Neuroimaging Data from Nationwide Consortiums for Mental Health Research [Info]

• Oral Presentation Session at International Conference on Machine Learning 2022 (role: Chair); Title: Theory [Info]

Reviewer

• International Conference on Machine Learning; Awarded Top 10% Reviewer
• JAMA Psychiatry
• Expert Systems with Applications
• Pattern Recognition Letters
• International Conference on Artificial Intelligence and Statistics
• International Journal of Computer Assisted Radiology and Surgery