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 Dr. Eun-Sol Kim). 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.

Junhyun Lee

[ dʒun.hjʌn liː ]

Ph.D. candidate
Email : leejhyun33 [at] gmail [dot] com / ljhyun33 [at] korea [dot] ac [dot] kr

Selected Publications

(*Equal contribution)


Ph.D. in Computer Science & Engineering at Korea University
[2018 - present]

Data Mining & Information Systems Lab (advisor: Prof. Jaewoo Kang)

Visiting Scholar at Carnegie Mellon University
[JAN 2020 - JUL 2020]

- AI Program at Language Technologies Institute
- Data Analysis Techniques Algorithms Lab (advisor: Prof. Leman Akoglu)

B.S. in Biomedical Engineering at Korea University
[2011 - 2017]

Intelligent Bio-MEMS Lab (advisor: Prof. Sang-Hoon Lee)

Work Experience

LG AI Research @South Korea
[MAY 2024 - present]

AI Research Intern Multimodal lab (leader: Dr. Soonyoung Lee)
- Medical squad (leader: Dr. Jongseong Jang)
- Performed research on medical data analysis

Online Course Instructor at FastCampus @South Korea
[JUN 2022]

Instructor High-level computer vision course
- Designed and implemented curriculum for graph and transformer-based approaches

Kakao Brain @South Korea
[DEC 2020 - JUN 2021]

AI Research Intern Video intelligence team (host: Dr. Eun-Sol Kim)
- Performed research on high-level computer vision for video understanding

Industry-Academia Collaboration Foundation, Korea Univ. @South Korea
[JUN 2017 - FEB 2018]

Researcher Big data scientist training team (host: Prof. Jaewoo Kang)

Intelligent Bio-MEMS Lab, Korea Univ. @South Korea
[DEC 2015 - JUN 2016]

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


Deep Learning for Graph-structured Biomedical Data
[2018 - present]

- 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

Web development (Back-end & Front-end)
[2018 - present]

- 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

Application of Deep Learning in Medical Image analysis [Github ★2.4k+]
[2017 - 2018]

- Developed object detection model for white blood cell microscopic image
- Implemented medical image segmentation model
- Developed labeling tool (PyQt 5) for medical image segmentation

Clinical Decision Support System for Depression

- Performed a precedent study for clinical decision support system about deep learning
- Developed the webserver for deep learning model inference APIs (Flask)

Development of Human-Machine Interfaces [link to the paper]
[2015 - 2016]

- 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)

ECG (EKG) Authentication (Biometrics) System [link to the post]
[2015 - 2016]

- 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

Kiosk Production for Reading Room [link to Univ News Article (Korean)]
[2015 - 2016]

- 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

[Organizer, Founder] GNN KR (2.4k+ members) [link to Facebook group]
[2019 - present]

A Korean community for Graph Neural Networks

[Organizer, Reviewer] Graph Conferences and Workshops
[2022 - present]

- [Organizer, Reviewer] Learning on Graphs Conference
- [Program Committee] Graph Learning Workshop at The Web Conference 2022 [link to web archive]

[Reviewer] Machine Learning Conferences
[2021 - present]

- International Conference on Learning Representations (ICLR)
- International Conference on Machine Learning (ICML)
- Conference on Neural Information Processing Systems (NeurIPS)

[Reviewer] Computer Vision Conferences
[2023 - present]

- IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- IEEE International Conference on Computer Vision (ICCV)
- European Conference on Computer Vision (ECCV)

[Reviewer] Data Mining Conferences
[2024 - present]

- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

[Reviewer] Journals

- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- Information Sciences
- Computer Vision and Image Understanding (CVIU)

[Talk] Introduction to Graph Neural Networks
[MAR 2020]

Cleveland Clinic @Ohio, USA

[Talk] Invited paper: Self-Attention Graph Pooling
[JUN 2019]

Korea Computer Congress @Jeju, South Korea

[Talk] Introduction to Graph Neural Networks
[JUL 2019]

Kakao Corp. @Pangyo, South Korea

Honors and Scholarships

ECCV 2020 VOT2020-LT challenge 5th prize winner
[Challenge paper] [Challenge page]
DREAM challenge Top performer
[Challenge paper] [Challenge page]

IDG-DREAM Drug-Kinase binding prediction challenge (Team: DMIS_DK)

Research Scholarship ($10,000)
[2021 - 2022]
AI Program at Carnegie Mellon University supported by Korean Government ($43,000)
Travel Grant for ICML conference by Kakao Corp. ($3,000)
General Scholarship ($1,000)
BK(Brain Korea)21Plus Scholarship ($15,000)
[2018 - 2020]
National Science and Engineering Scholarship ($4,000)
KU Undergraduate Research Scholarship ($1,000)
University Volunteer Scholarship ($600)

Scholarship due to a volunteer kiosk project [link to Univ News Article (Korean)]

Academic Excellence Scholarship ($2,000)
The scholarship amounts shown above are approximate.

Patents (as an inventor)

[South Korea] Method and system for discovery new drug candidate

[link to Google Patents page]

[South Korea] Conductive polymer composite

[link to Google Patents page]

[International, PCT] Method and system for recommending antidepressants

[link to Google Patents page]

[International, PCT] Method for preparing conductive polymer composite and conductive polymer composite prepared therefrom

[link to Google Patents page]

[South Korea] System for recommending personalized antidepressants and quantitatively predicting reactivity of antidepressants