Publications
Journal
[J1] Kim, S., Kim, Y.-G., and Wang, Y. (2024). Temporal generative models for learning heterogeneous group dynamics of ecological momentary data. Biometrics [Paper] [Code]
[J2] Kim, Y.-G.*, Ravid, O.*, Zhang, X., Kim, Y., Neria, Y., Lee, S., He, X.‡, and Zhu, X.‡ (2024). Explaining deep learning-based representations of resting state functional connectivity data: focusing on interpreting nonlinear patterns in autism spectrum disorder. Frontiers in Psychiatry. [Paper] [Code] *: Equal contribution of the first authors; ‡: Equal contribution of the corresponding authors
[J3] Kim, Y.-G., Lee, K., and Paik, M.C. (2022). Conditional Wasserstein generator. IEEE Transactions on Pattern Analysis and Machine Intelligence. [Paper] [Code]
[J4] 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]
Peer-reviewed Conference
[C1] Kim, Y.-G., Hu, M.-C., Nunes, E. V., Luo, S. X.‡, and Liu, Y.‡ (2025). Optimizing contingency management with reinforcement learning. Accepted at IEEE International Conference on Healthcare Informatics (selected as a long presentation) [PreliminaryVersion] [Code] ‡: Equal contribution of the corresponding authors
[C2] 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]
[C3] Kim, M., Kim, Y.-G., Kim, D., Kim, Y., and Paik, M.C. (2021). Kernel-convoluted deep neural networks with data augmentation. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2021). [Paper] [Code]
[C4] 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]
Patent
[P1] Paik, M.C., Kim, Y.-G., and Lee, K. (2024). Method and apparatus for conditional data generation using conditional Wasserstein generator. KR Patent 102734936B1. [Info]
[P2] Paik, M.C., Kim, Y.-G., and Chang, H. (2021). Learning method and learning device for high-dimension unsupervised anomaly detection using kernalized Wasserstein autoencoder to lessen too many computations of Christophel function, and testing method and testing device using the same. KR Patent 102202842B1. [Info]
Preprint
[Pre. 1] Kim, Y.-G., Lee, K., Choi, Y., Won, J.-H., and Paik, M.C. (2023). Wasserstein geodesic generator for conditional distributions (under Major Revision at Journal of Machine Learning Research). [ArXiv] [Code]
[Pre. 2] Zheng, X., Ravid, O., Barry, R. A.J., Kim, Y., Wang, Q., Kim, Y.-G., Zhu, X.‡ and He, X.‡ (2024). Denoising Variational Autoencoder as a Feature Reduction Pipeline for the diagnosis of Autism based on Resting-state fMRI. [Arxiv] ‡: Equal contribution of the corresponding authors
Work in progress
[W1] Kim, Y.-G.*‡ and Liu, Y. Mid-VAE: Multi-modal, Identifiable, and Disentangled Representation Learning for Children’s Structural Brain Imaging. Work in progress
- Preliminary results were presented at ABCD AIIM conference.
[W2] Yang B., Kim, Y.-G., and Wang Y. Representation learning for optimizing individualized treatment decisions. Work in progress
- This work was selected as the Runner-up in the student paper competition for the Statistics in Imaging Section of the ASA.
[W3] Yu, W., Qu, G., Kim, Y.-G., Xu, L., and Zhang, A (2025). A Novel GNN Framework Integrating Neuroimaging and Behavioral Information to Understand Adolescent Psychiatric Disorders (Submitted to MIDL 2025)