Department of Aritificial Intelligence, Inha University, Incheon, Korea
Contact me by email at kyungeun.lee@inha.ac.kr.
[ 학부 연구생 또는 석/박사 진학을 희망하는 학생들은 위 메일로 연락주세요 😀 ]
CV / Google Scholar / LinkedIn
Current Research Interests: Representation Learning, with a focus on
(1) generalization in deep neural networks,
(2) applications to tabular data, and
(3) multimodal learning with tabular data.
Collaboration: Research on tabular learning with LG AI Research
News
[2025.9.1] I started giving lectures at Inha University.
[2025.5.15] Our paper on few-shot learning in tabular domain is accepted at KDD 2025!
[2024.12.10] Two papers on tabular learning and OOD detection are accepted at AAAI 2025!
[2024.9.26] Our paper on MI estimation is accepted at NeurIPS 2024!
[2024.8.2] Our paper on MI analysis in contrastive representation learning has been published in Neural Networks!
[2024.5.1] Our paper on tabular representation learning is accepted at ICML 2024!
[2024.4.2] Our team received 2024 LG Award.
[2024.2.24] I received Ph.D. from Seoul National University (Advisor: Wonjong Rhee).
[2024.1.16] I started to work at LG AI Research (Advisor: Woohyung Lim).
[2022.11.25] I received Yulchon AI Young Researcher scholarship. Only ten selected students in Seoul National University received the scholarship!
Education
Seoul National University, Department of Intelligence and Information, Graduate School of Convergence Science and Technology
Ph.D. [2016.9 - 2023.2]
Advisor: Wonjong Rhee
Thesis: Understanding Mutual Information in Contrastive Representation Learning
Seoul National University, Civil and Environmental Engineering
B.S. [2010.3 - 2014.2]
Kangwon Science High School
Early graduation [2008.3 - 2010.2]
Careers
Inha University, Incheon, South Korea
Assistant professor, Department of Artificial intelligence [2025.9 - Present]
LG AI Research, Seoul, South Korea
AI Research at Data Intelligence Lab. [2023.1 - 2025.8]
The Cyber University of Korea, Seoul, South Korea
Visiting Professor [2024.3 - 2025.2]
Samsung Engineering, Seoul, South Korea
Supervisor engineer [2014.3 - 2015.3]
Publication
Preprints (either available on arXiv or currently under peer review)
MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular Domains
Kyungeun Lee, Moonjung Eo, Hye-Seung Cho, Dongmin Kim, Ye Seul Sim, Seoyoon Kim, Min-Kook Suh, Woohyung Lim (2025)
Anomaly Detection Framework in Tabular Domains (Tentative title)
Hye-Seung Cho & Moonjung Eo, Kyungeun Lee, Min-Kook Suh, Seoyoon Kim, Sanghyu Yoon, Dongmin Kim, Woohyung Lim (2025)
Enhancing Tabular Foundation Models (Tentative title)
Kyungeun Lee (2025)
Enhancing Embedding Modules in Tabular Learning (Tentative title)
Min-Kook Suh, Moonjung Eo, Kyungeun Lee, Seoyoon Kim, Hye-Seung Cho, Woohyung Lim (2025)
Conference & Workshop
Range-limited Augmentation for Few-shot Learning in Tabular Data with Comprehensive Benchmark
Kyungeun Lee, Moonjung Eo, Hye-Seung Cho, Min-Kook Suh, Seoyoon Kim, Ye Seul Sim, Suhee Yoon, Sanghyu Yoon, Woohyung Lim (2025)
31st SIGKDD Conference on Knowledge Discovery and Data Mining - Research track (Acceptance rate: 18.4%)
Representation Space Augmentation for Effective Self-Supervised Learning on Tabular Data
Moonjung Eo, Kyungeun Lee, Hye-Seung Cho, Dongmin Kim, Ye Seul Sim, Woohyung Lim (2025)
AAAI Conference on Artificial Intelligence (AAAI).
Diffusion-based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection
Suhee Yoon, Sanghyu Yoon, Hankook Lee, Ye Seul Sim, Sungik Choi, Kyungeun Lee, Hye-Seung Cho, Woohyung Lim (2025)
AAAI Conference on Artificial Intelligence (AAAI).
A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
Kyungeun Lee, Wonjong Rhee (2024)
Conference on Neural Information Processing Systems (NeurIPS) (Datasets & Benchmarks Track)
Best international conference for the subject area of artificial intelligence (h5-index 337) (https://scholar.google.es/citations? view_op=top_venues&hl=en&vq=eng_artificialintelligence). Acceptance rate: 25.3% (460 / 1,820)
AGATa: Attention-Guided Augmentation for Tabular Data in Contrastive Learning
Moonjung Eo, Kyungeun Lee, Min-Kook Suh, Hyeseung Cho, Ye Seul Sim, Woohyung Lim (2024)
NeurIPS Workshop (Table Representation Learning)
Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
Kyungeun Lee, Ye Seul Sim, Hyeseung Cho, Moonjung Eo, Suhee Yoon, Sanghyu Yoon, Woohyung Lim (2024)
International Conference on Machine Learning (ICML) & NeurIPS Workshop (Table Representation Learning)
Top 3 of the international conference for the subject area of artificial intelligence (h5-index 254) (https://scholar.google.es/citations? view_op=top_venues&hl=en&vq=eng_artificialintelligence). Acceptance rate: 27.5% (2,609 / 9,473)
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 (2023)
NeurIPS Workshop (SyntheticData4ML)
Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion
Jungwook Shin, Jaeill Kim, Kyungeun Lee, Hyunghun Cho, Wonjong Rhee (2023)
AAAI Conference on Artificial Intelligence (AAAI). (Oral)
Top 4 of the international conference for the subject area of artificial intelligence (h5-index 180) (https://scholar.google.es/citations? view_op=top_venues&hl=en&vq=eng_artificialintelligence). Acceptance rate: 19.6% (1,721 / 8,777)
Statistical Characteristics of Deep Representations: An Empirical Investigation
Kyungeun Lee & Daeyoung Choi, Duhun Hwang, Wonjong Rhee (2021)
International Conference on Artificial Neural Networks (ICANN). (Equal contribution.)
딥러닝 모델을 활용한 교통 혼잡도 예측 및 Geometric 딥러닝 모델의 활용방안
이경은, 어문정, 김세동, 정은아, 이원종 (2018)
한국경영과학회 학술대회논문집, 912-918.
Who Should Participate in DR Program? Modeling with Machine Learning and Credit Scoring
Kyungeun Lee, Eunjung Lee, Hyesu Lee, Hyoseop Lee, Yoonjin Yoon, Wonjong Rhee (2017)
BEHAVIOR, ENERGY & CLIMATE CHANGE CONFERENCE. American Council for an Energy Efficient Economy, Precourt Energy Efficiency Center, Berkeley Energy and Climate Institute.
딥러닝 적용을 통한 공역 혼잡도 및 리스크 모델링: 도로교통데이터 분석 방식을 벤치마킹한 접근
이경은, 이원종 (2017)
한국경영과학회 학술대회논문집, 243-248. (KCI)
Journal
Towards a rigorous analysis of mutual information in contrastive learning
Kyungeun Lee, Jaeill Kim, Suhyun Kang, Wonjong Rhee (2024)
Neural Networks, 106584. [SCIE, IF: 6.0, JCR: 1.54]
DDP-GCN: Multi-graph convolutional network for spatiotemporal traffic forecasting
Kyungeun Lee, Wonjong Rhee (2022)
Transportation Research Part C: Emerging Technologies, 134, 103466. [SCIE, IF: 9.022, JCR: 6.72]
Top 2% of citations and captures among the papers published in the same year
Among SCI journals, the top 0.61% (2/328) for the subject area of civil and structural engineering, the top 3.29% (24/729) for the subject area of computer science applications, the top 3.29% (62/1886) for the subject area of computer science, the top 1.67% (51/3061) for the subject area of engineering, and the top 4.24% (5/118) for the subject area of transportation. (https://www.scimagojr.com/, 2021.)
Short-term traffic prediction with deep neural networks: A survey
Kyungeun Lee, Moonjung Eo, Euna Jung, Yoonjin Yoon, Wonjong Rhee (2021)
IEEE Access, 9, 54739-54756. [SCIE, IF: 3.367]
Defining virtual control group to improve customer baseline load calculation of residential demand response
Eunjung Lee, Kyungeun Lee, Hyoseop Lee, Euncheol Kim, Wonjong Rhee (2019)
Applied Energy, 250, 946-958. [SCIE, IF: 8.85, JCR: 5.31]
Among SCI journals, the top 1.83% (56/3061) for the subject area of engineering, the top 3.73% (20/536) for the subject area of energy, and the top 1.40% (23/1645) for the subject area of environmental science. (https://www.scimagojr.com/, 2021.)
Assuring explainability on demand response targeting via credit scoring
Kyungeun Lee, Hyesu Lee, Hyoseop Lee, Yoonjin Yoon, Eunjung Lee, Wonjong Rhee (2018)
Energy, 161, 670-679. [SCIE, IF: 6.23, JCR 4.55]
Among SCI journals, the top 8.21% (44/536) for the subject area of energy, the top 4.64% (142/3061) for the subject area of engineering, the top 5.27% (88/1670) for the subject of mathematics. (https://www.scimagojr.com/, 2021.)
Extended TAM Analysis of a Residential DR Pilot Program
Euna Jung, Kyungeun Lee, Hwayoung Kim, Sora Jeong, Hyoseop Lee, Bongwon Suh, Wonjong Rhee (2017)
Journal of the HCI Society of Korea, 12(4), 65-73. (KCI)
Role of Demand Response in Small Power Consumer Market and a Pilot Study
Eunjung Lee, Kyungeun Lee, Hyoseop Lee, Euncheol Kim, Wonjong Rhee (2017)
The Journal of Korean Institute of Communications and Information Sciences, 42(4), 915-922. (KCI)
Scholarship and Awards
LG Award, LG (2024)
Yulchon AI Young Researcher Scholarship, Seoul National University (2022) [Link]
Teaching Assistants Scholarship, Seoul National University (2021)
Merit-based Scholarship, Seoul National University (2019, 2010)
Dearim Suam Scholarship, Daerim Suam Scholarship Foundation (2011 - 2013)
Samsung SDS Scholarship, Samsung SDS (2009 - 2013)
Teaching and Activities
Advanced AI lecturer, The Graduate School of the Cyber University of Korea (2024)
Deep Learning lecturer, The Cyber University of Korea (2024)
Information Theory TA, Seoul National University (2021)
Data Science TA, Seoul National University Coorperation R&D Center, Samsung (2019)
Special Lecture, Wooseok Middle School (2019)
Deep Learning TA, Seoul National University (2018)
Machine Learning TA, Seoul National University (2016)
Deep Representation Learning Research Group Internship, Seoul National University (2016)
Selected Projects
Quality prediction and anomaly detection in manufacturing systems, LG AI Research (2023 - Present)
Traffic management system design and speed prediction, Seoul National University, KAIST (2017 - 2019)
Demand response pilot program design and evaluation for 31,615 residential customers, Seoul National University, Korea Power Exchange, LG Uplus, Encodered Technologies (2016 - 2018)
Professional Service
Reviewer: NeurIPS(2024), ICML(2024, 2025), ICLR(2025), KDD(2025 -- Excellent reviewer!), AISTATS(2025), AAAI(2026)