Hello! I am currently a PhD candidate in the Computer Science & Engineering Department at Korea University and a member of Data Mining and Information Systems (DMIS) Lab, advised by Prof. Jaewoo Kang (and co-advised by Prof. Hyunwoo J. Kim for a year). During my PhD course, I completed the Intensive Artificial Intelligence Program at Carnegie Mellon University and studied as a visiting student advised by Prof. Leman Akoglu. I worked as an AI research intern at KakaoBrain for six months (hosted by Eun-Sol Kim, Ph.D.). Prior to my PhD studies, I received a Bachelor's degree in Biomedical Engineering from Korea University.
My research area covers the broad field of machine learning, with a focus on representation learning for graph-structured data. I am also interested in applying machine learning techniques to diverse domains, including computer vision and bioinformatics.
[ dʒun.hjʌn liː ]
Selected Publications
(*Equal contribution)-
[Under Review] Beyond Association: A Causal Perspective on Multi-Resolution Aggregation in Multiple-Instance Learning for Whole Slide Image Analysis
Junhyun Lee, Soonyoung Lee, Jongseong Jang
-
[Under Review] Mitigating Multi-Resolution Dilemma of Whole Slide Images via Spectral Approaches
Junhyun Lee, Jongseong Jang, Soonyoung Lee, Bumsoo Kim
-
[Under Review] Subgraph-level Universal Prompt Tuning
Junhyun Lee, Wooseong Yang, Jaewoo Kang
-
[Under Review] Understanding and Tackling Over-Dilution in Graph Neural Networks
Junhyun Lee, Veronika Thost, Bumsoo Kim, Jaewoo Kang, Tengfei Ma
-
[Under Review] CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement
Seungheun Baek*, Soyon Park*, Yan Ting Chok, Junhyun Lee, Jueon Park, Mogan Gim, Jaewoo Kang
-
[NeurIPS 2024] TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
Kiwoong Yoo, Owen Oertell, Junhyun Lee, Sanghoon Lee, Jaewoo Kang
-
[Bioinformatics / ISMB 2024] MolPLA: A Molecular Pretraining Framework for Learning Cores, R-Groups and their Linker Joints
Mogan Gim*, Jueon Park*, Soyon Park, Sanghoon Lee, Seungheun Baek, Junhyun Lee, Ngoc-Quang Nguyen, Jaewoo Kang
-
[IEEE Access 2023] Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
Junhyun Lee*, Bumsoo Kim*, Minji Jeon, Jaewoo Kang
-
[ECAI 2023] Towards Flexible Time-to-event Modeling: Optimizing Neural Networks via Rank Regression
Hyunjun Lee*, Junhyun Lee*, Taehwa Choi, Jaewoo Kang, Sangbum Choi
-
[CVPR 2022] MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection
Bumsoo Kim, Jonghwan Mun, Kyoung-Woon On, Minchul Shin, Junhyun Lee, Eun-Sol Kim
-
[NeurIPS 2021] Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
Seongjun Yun, Seoyoon Kim, Junhyun Lee, Jaewoo Kang, Hyunwoo J. Kim
-
[CVPR 2021 (Oral)] HOTR: End-to-End Human-Object Interaction Detection with Transformers (Cited by over 200)
Bumsoo Kim, Junhyun Lee, Jaewoo Kang, Hyunwoo J Kim, Eun-sol Kim
-
[ACS Appl. Mater. Interfaces 2020] 3D Printed, Customizable, and Multifunctional Smart Electronic Eyeglasses for Wearable Healthcare Systems and Human–Machine Interfaces
Joong Hoon Lee, Hanseop Kim, Ji-Young Hwang, Jinmook Chung, Tae-Min Jang, Dong Gyu Seo, Yuyan Gao, Junhyun Lee, Haedong Park, Seungwoo Lee, Hong Chul Moon, Huanyu Cheng, Sang-Hoon Lee, Suk-Won Hwang
-
[ECCV 2020 Workshop] Robust Long-Term Object Tracking via Improved Discriminative Model Prediction
Seokeon Choi, Junhyun Lee, Yunsung Lee, Alexander Hauptmann
-
[ICML 2019] Self-Attention Graph Pooling (Cited by over 1,000)
Junhyun Lee*, Inyeop Lee*, Jaewoo Kang
Education
Data Mining & Information Systems Lab (advisor: Prof. Jaewoo Kang)
- AI Program at Language Technologies Institute
- Data Analysis Techniques Algorithms Lab (advisor: Prof. Leman Akoglu)
Intelligent Bio-MEMS Lab (advisor: Prof. Sang-Hoon Lee)
Work Experience
AI Research Intern Multimodal lab (leader: Soonyoung Lee, Ph.D.)
- Medical squad (leader: Jongseong Jang, Ph.D.)
- Performed research on medical data analysis
Instructor High-level computer vision course
- Designed and implemented curriculum for graph and transformer-based approaches
AI Research Intern Video intelligence team (host: Eun-Sol Kim, Ph.D.)
- Performed research on high-level computer vision for video understanding
Researcher Big data scientist training team (host: Prof. Jaewoo Kang)
Research Intern Biomedical electrode team (host: Prof. Sang-Hoon Lee)
- Developed human-machine interface applications using biomedical signals
- Fabricated the elastic electrode with carbon nanotube and polydimethylsiloxane
Projects
- Developed a novel deep learning model to generate molecular graph representations and integrate gene expression data
- Constructed drug-kinase binding affinity prediction model
- Developed a novel graph pooling module to predict drug-drug interactions
- Developed the webserver (Back-end) by using Django, Nginx, and Gunicorn
- Developed Front-end by using HTML, CSS and JavaScript
- Served on both RaspberryPi (for hardware interactions) and AWS
- URL: https://zozo.works
- URL: https://fromzero.studio
- Developed object detection model for white blood cell microscopic image
- Implemented medical image segmentation model
- Developed labeling tool (PyQt 5) for medical image segmentation
- Performed a precedent study for clinical decision support system about deep learning
- Developed the webserver for deep learning model inference APIs (Flask)
- Fabricated composite of carbon nanotube and polydimethylsiloxane
- Performed toxicity test of the electrode with HaCaT cell line
- Developed a Human-Machine Interface Application using EOG (Electrooculography)
- Developed the end-to-end wireless authentication system using ECG(ElectroCardioGram)
- Fabricated the elastic electrode with carbon nanotube and polydimethylsiloxane
- Designed analog signal processing circuit and DAQ
- Developed Bluetooth communication, digital signal processing, and GUI
- Developed programs for generation of personal barcodes and a barcode reader
- Developed a kiosk program for college reading room seat allocation [link to photos]
Academic Activities
A Korean community for Graph Neural Networks
- [Organizer, Reviewer] Learning on Graphs Conference
- [Program Committee] Graph Learning Workshop at The Web Conference 2022 [link to web archive]
- International Conference on Learning Representations (ICLR)
- International Conference on Machine Learning (ICML)
- Conference on Neural Information Processing Systems (NeurIPS)
- IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- IEEE International Conference on Computer Vision (ICCV)
- European Conference on Computer Vision (ECCV)
- Asian Conference on Computer Vision (ACCV)
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- Information Sciences
- Computer Vision and Image Understanding (CVIU)
- Engineering Applications of Artificial Intelligence (EAAI)
- Neurocomputing
Cleveland Clinic @Ohio, USA
Korea Computer Congress @Jeju, South Korea
Kakao Corp. @Pangyo, South Korea
Honors and Scholarships
IDG-DREAM Drug-Kinase binding prediction challenge (Team: DMIS_DK)
Scholarship due to a volunteer kiosk project [link to Univ News Article (Korean)]