Hankook Lee
hankook.lee at skku.edu / Github / Google ScholarI am an assistant professor in Department of Computer Science and Engineering at Sungkyunkwan University (SKKU). Prior to this, I worked at LG AI Research as a Research Scientist and Korea Advanced Institute of Science and Technology (KAIST) as a Postdoctoral Researcher. I completed my Ph.D. degree in the School of Electrical Engineering at KAIST, advised by Prof. Jinwoo Shin.
I am interested in improving the efficiency of deep learning. Specifically, my research has focused on data-efficient deep learning, including self-supervised learning, few-shot learning, and transfer learning. I am also interested in solving real-world problems on various data domains such as computer vision, chemistry, and tabular data.
Efficient Learning Lab (ELL) at SKKU. I am currently looking for self-motivated graduate students and undergraduate interns with a strong interest in the area of deep learning. If you are interested in joining our lab, send me an email with your transcript and CV.
Publications
J: Journal / C: Conference / W: Workshop / *: equal contribution
- [C15] Learning Equi-angular Representations for Online Continual Learning
- Minhyuk Seo, Hyunseo Koh, Wonje Jeung, Min Jae Lee, San Kim, Hankook Lee, Sungjun Cho, Sungik Choi, Hyunwoo Kim, Jonghyun Choi
Conference on Computer Vision and Pattern Recognition (CVPR), 2024 - [J1/W] Few-shot Anomaly Detection via Personalization
- Sangkyung Kwak, Jongheon Jeong, Hankook Lee, Woohyuck Kim, Dongho Seo, Woojin Yun, Wonjin Lee, Jinwoo Shin
IEEE Access, 2024
ICML Workshop on New Frontiers in Adversarial Machine Learning (AdvML-Frontiers), 2023
[paper] - [C14] Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models
- Sungik Choi, Hankook Lee, Honglak Lee, Moontae Lee
Neural Information Processing Systems (NeurIPS), 2023
[paper] - [W3] Diffusion-based Semantic-Discrepant Outlier Generation for Out-of-Distribution Detection
- Suhee Yoon*, Sanghyu Yoon*, Hankook Lee, Sangjun Han, Ye Seul Sim, Kyungeun Lee, Hyeseung Cho, Woohyung Lim
NeurIPS Workshop on Synthetic Data Generation with Generative AI (SyntheticData4ML), 2023
[paper] - [W2] Mixed-Curvature Transformers for Graph Representation Learning
- Sungjun Cho, Seunghyuk Cho, Sungwoo Park, Hankook Lee, Honglak Lee, Moontae Lee
ICML Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML), 2023
[paper] - [W1] Fragment-based Multi-view Molecular Contrastive Learning
- Seojin Kim*, Jaehyun Nam*, Junsu Kim, Hankook Lee, Sungsoo Ahn, Jinwoo Shin
ICLR Workshop on Machine Learning for Materials (ML4Materials), 2023
[paper] - [C13/W] Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
- Jongheon Jeong, Sihyun Yu, Hankook Lee, Jinwoo Shin
Computer Vision and Pattern Recognition (CVPR), 2023
ECCV Workshop on Out-of-distribution Generalization in Computer Vision (ECCVW-OOD-CV), 2022
[paper] [arxiv] - [C12/W] STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
- Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, Jinwoo Shin
International Conference on Learning Representations (ICLR), Spotlight presentation, 2023
Neural Information Processing Systems Workshop on Table Representation Learning (NeurIPSW-TRL), 2022
Samsung Humantech Paper Awards, Bronze Prize, 2023
[paper] [code] - [C11/W] Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning
- Huiwon Jang*, Hankook Lee*, Jinwoo Shin
International Conference on Learning Representations (ICLR), Spotlight presentation, 2023
Neural Information Processing Systems Workshop on Meta-Learning (NeurIPSW-MetaLearn), 2022
[paper] [arxiv] [code] - [C10/W] Guiding Energy-based Models via Contrastive Latent Variables
- Hankook Lee, Jongheon Jeong, Sejun Park, Jinwoo Shin
International Conference on Learning Representations (ICLR), Spotlight presentation, 2023
Neural Information Processing Systems Workshop on Self-Supervised Learning (NeurIPSW-SSL), Oral Presentation, 2022
[paper] [arxiv] [code] - [C9] Meta-Learning with Self-Improving Momentum Target
- Jihoon Tack, Jongjin Park, Hankook Lee, Jaeho Lee, Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2022
[paper] [arxiv] [slide] [poster] [code] - [C8] Patch-level Representation Learning for Self-supervised Vision Transformers
- Sukmin Yun, Hankook Lee, Jaehyung Kim, Jinwoo Shin
Computer Vision and Pattern Recognition (CVPR), Oral Presentation, 2022
[paper] [arxiv] [poster] [code] - [C7/W] Improving Transferability of Representations via Augmentation-Aware Self-Supervision
- Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee, Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2021
ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception
[paper] [arxiv] [slide] [poster] [code] - [C6] Self-Improved Retrosynthetic Planning
- Junsu Kim, Sungsoo Ahn, Hankook Lee, Jinwoo Shin
International Conference on Machine Learning (ICML), 2021
[paper] [arxiv] [slide] [poster] [code] - [C5/W] RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
- Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung Ju Hwang, Jinwoo Shin
International Joint Conference on Artificial Intelligence (IJCAI), 2021
NeurIPS Workshop for Machine Learning for Molecules, 2020
[paper] [arxiv (long version)] [slide] [poster] [code] - [C4] GTA: Graph Truncated Attention for Retrosynthesis
- Seung-Woo Seo*, You Young Song*, June Yong Yang, Seohui Bae, Hankook Lee, Jinwoo Shin, Sung Ju Hwang, Eunho Yang
AAAI Conference on Artificial Intelligence (AAAI), 2021
[paper] - [C3] Guiding Deep Molecular Optimization with Genetic Exploration
- Sungsoo Ahn, Junsu Kim, Hankook Lee, Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2020
[paper] [arxiv] [code] - [C2] Self-supervised Label Augmentation via Input Transformations
- Hankook Lee, Sung Ju Hwang, Jinwoo Shin
International Conference on Machine Learning (ICML), 2020
Qualcomm-KAIST Innovation Awards, 2019
[paper] [arxiv] [code] [talk] - [C1] Learning What and Where to Transfer
- Yunhun Jang*, Hankook Lee*, Sung Ju Hwang, Jinwoo Shin
International Conference on Machine Learning (ICML), 2019
[paper] [arxiv] [code] [slide] [talk 55:14~59:09]
Work Experience
- Sungkyunkwan University
- Suwon, South Korea, 2024. 03 - present
Assistant Professor - LG AI Research
- Seoul, South Korea, 2023. 02 - 2024. 02
Research Scientist - Korea Advanced Institute of Science and Technology (KAIST)
- Seongnam, South Korea, 2022. 09 - 2023. 02
Postdoctoral Researcher - Samsung Advanced Institute of Technology (SAIT)
- Suwon, South Korea, 2020. 01 - 2020. 03
Visiting Student - Frograms Inc. (changed to Watcha Inc. @ 2018)
- Seoul, South Korea, 2013. 08 - 2014. 12
Research and Development Engineer
Education
- Korea Advanced Institute of Science and Technology (KAIST)
- Daejeon, South Korea, 2016. 03 - 2022. 08
M.S. & Ph.D. in Electrical Engineering (advisor: Jinwoo Shin) - Korea Advanced Institute of Science and Technology (KAIST)
- Daejeon, South Korea, 2010. 02 - 2016. 02
B.S. in Mathematical Science and Computer Science (double major)
Awards
- Qualcomm-KAIST Innovation Awards (2019)
- International Collegiate Programming Contest (ICPC)
- Asia Daejeon Regional: Grand Prize (1st place, 2012), Gold Prize (2nd place, 2010)
- Participated in ICPC World Finals 2013
- Korea Olympiad in Informatics (KOI) : Gold Prize (2009)
Services
- Area Chair
- NeurIPS (2024)
- Reviewer
- Conferences: ICLR (2020-2024), NeurIPS (2020-2023), ICML (2021-2024), AAAI (2022-2024)
- Conference Workshops: Self-supervised Learning (ICML 2021, NeurIPS 2021-2022, ECCV 2022)
- Journals: ACM ToMPECS, IEEE TPAMI, Journal of Machine Learning Research (JMLR), Nature Communications