Geon Lee

Geon Lee

Postdoctoral Researcher, KAIST
geonlee0325 [at] kaist.ac.kr
About

I am a Postdoctoral Researcher at the Information & Electronics Research Institute, KAIST, working with Prof. Kijung Shin at the Data Mining Lab. I received a Ph.D. degree in Artificial Intelligence at KAIST in 2026, advised by Prof. Kijung Shin, and won the Ph.D. Dissertation Award from the KAIST College of Engineering. I received my B.S. in Computer Science and Engineering from Sungkyunkwan University. During my Ph.D., I interned at Snap Research, NEC Labs America, and Amazon.

My research focuses on mining and learning on relational data (e.g., graphs, hypergraphs, and relational databases) as well as sequential data (e.g., time-series and user interaction sequences) and multi-modal data (e.g., text, visual, and tabular data). I am broadly interested in recommender systems, retrieval systems, and social network analysis. Recently, I have been interested in leveraging large language models (LLMs) to enhance learning and inference on relational and structured data, with a focus on developing frameworks that support complex and autonomous reasoning over real-world data.

Work Experience
KAIST
Postdoctoral Researcher
Mar 2026 – Present
Seoul, South Korea
Snap Research
Research Intern
Apr – Jun 2025
Bellevue, WA, USA
NEC Labs America
Research Intern
May – Aug 2023
Princeton, NJ, USA
Amazon
Applied Scientist Intern
Sep – Dec 2022
San Francisco, CA, USA
Education
KAIST
M.S. & Ph.D. in Artificial Intelligence
Sep 2020 – Feb 2026
Seoul, South Korea
Sungkyunkwan University
B.S. in Computer Science and Engineering
Mar 2016 – Aug 2019
Suwon, South Korea
Publications
2026
[C26] ReFuGe: Feature Generation for Prediction Tasks on Relational Databases with LLM Agents
Kyungho Kim, Geon Lee, Juyeon Kim, Dongwon Choi, Shinhwan Kang, and Kijung Shin
[C25] Sequential Data Augmentation for Generative Recommendation
Geon Lee, Bhuvesh Kumar, Clark Mingxuan Ju, Tong Zhao, Kijung Shin, Neil Shah, and Liam Collins
[J9] A Comprehensive Survey on Multi-Behavior Recommender Systems: Extended Taxonomy and Recent Advances
Kyungho Kim, Sunwoo Kim, Geon Lee, Jinhong Jung, and Kijung Shin
2025
[C24] RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases
Dongwon Choi, Sunwoo Kim, Juyeon Kim, Kyungho Kim, Geon Lee, Shinhwan Kang, Myunghwan Kim, and Kijung Shin
[C23] TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
Yushan Jiang, Wenchao Yu, Geon Lee, Dongjin Song, Kijung Shin, Wei Cheng, Yanchi Liu, and Haifeng Chen
[C22] Attributed Hypergraph Generation with Realistic Interplay Between Structure and Attributes
Jaewan Chun, Seokbum Yoon, Minyoung Choe, Geon Lee, and Kijung Shin
Best Paper Award
·
One of the Best-Ranked Papers
[C21] Identifying Group Anchors in Real-World Group Interactions Under Label Scarcity
Fanchen Bu, Geon Lee, Minyoung Choe, and Kijung Shin
[C20] A Self-Supervised Mixture-of-Experts Framework for Multi-behavior Recommendation
Kyungho Kim, Sunwoo Kim, Geon Lee, and Kijung Shin
[J8] Revisiting LightGCN: Unexpected Inflexibility, Inconsistency, and A Remedy Towards Improved Recommendation
Geon Lee, Kyungho Kim, Fanchen Bu, Langzhang Liang, and Kijung Shin
[C19] SkySearch: Satellite Video Search at Scale
Minyoung Choe*, Geon Lee*, Changhun Han*, Suji Kim, Woong Hu, Hyebeen Hwang, Geunseok Park, Byeongyeon Kim, Hyesook Lee, Ha-Myung Park, and Kijung Shin
[C18] KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking
Juyeon Kim, Geon Lee, Taeuk Kim, and Kijung Shin
[C17] MARIOH: Multiplicity-Aware Hypergraph Reconstruction
Kyuhan Lee, Geon Lee, and Kijung Shin
[J7] A Survey on Hypergraph Mining: Patterns, Tools, and Generators
Geon Lee*, Fanchen Bu*, Tina Eliassi-Rad, and Kijung Shin
[C16] Multi-Behavior Recommender Systems: A Survey
Kyungho Kim, Sunwoo Kim, Geon Lee, Jinhong Jung, and Kijung Shin
Best Survey Paper Award
[C15] Beyond Neighbors: Distance-Generalized Graphlets for Enhanced Graph Characterization
Yeongho Kim, Yuyeong Kim, Geon Lee, and Kijung Shin
[C14] TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents
Geon Lee, Wenchao Yu, Kijung Shin, Wei Cheng, and Haifeng Chen
2024
[C13] Resource2Box: Learning to Rank Resources in Distributed Search Using Box Embedding
Ulugbek Ergashev, Geon Lee, Kijung Shin, Eduard Dragut, and Weiyi Meng
[C12] Revisiting LightGCN: Unexpected Inflexibility, Inconsistency, and A Remedy Towards Improved Recommendation
Geon Lee, Kyungho Kim, and Kijung Shin
Best Short Paper Candidate
[C11] Post-Training Embedding Enhancement for Long-Tail Recommendation
Geon Lee, Kyungho Kim, and Kijung Shin
[C10] Towards Better Utilization of Multiple Views for Bundle Recommendation
Kyungho Kim, Sunwoo Kim, Geon Lee, and Kijung Shin
[J6] Representative and Back-in-Time Sampling from Real-World Hypergraphs
Minyoung Choe, Jaemin Yoo, Geon Lee, Woonsung Baek, U Kang, and Kijung Shin
[C9] VilLain: Self-Supervised Learning on Homogeneous Hypergraphs without Features via Virtual Label Propagation
Geon Lee, Soo Yong Lee, and Kijung Shin
2023
[T2] Mining of Real-World Hypergraphs: Patterns, Tools, and Generators
Geon Lee, Jaemin Yoo, and Kijung Shin
[J5] Random Walk with Restart on Hypergraphs: Fast Computation and an Application to Anomaly Detection
Jaewan Chun, Geon Lee, Kijung Shin, and Jinhong Jung
[J4] Hypergraph Motifs and Their Extensions Beyond Binary
Geon Lee*, Seokbum Yoon*, Jihoon Ko, Hyunju Kim, and Kijung Shin
KAIST Outstanding Paper Award
[J3] Hypercore Decomposition for Non-Fragile Hyperedges: Concepts, Algorithms, Observations, and Applications
Fanchen Bu, Geon Lee, and Kijung Shin
[J2] Temporal Hypergraph Motifs
Geon Lee and Kijung Shin
2022
[T1] Mining of Real-World Hypergraphs: Patterns, Tools, and Generators
Geon Lee, Jaemin Yoo, and Kijung Shin
[C8] Set2Box: Similarity Preserving Representation Learning for Sets
Geon Lee, Chanyoung Park, and Kijung Shin
[C7] HashNWalk: Hash and Random Walk Based Anomaly Detection in Hyperedge Streams
Geon Lee, Minyoung Choe, and Kijung Shin
[C6] MiDaS: Representative Sampling from Real-World Hypergraphs
Minyoung Choe, Jaemin Yoo, Geon Lee, Woonsung Baek, U Kang, and Kijung Shin
[J1/W1] Simple Epidemic Models with Segmentation Can Be Better than Complex Ones
Geon Lee, Se-eun Yoon, and Kijung Shin
2021
[C5] THyMe+: Temporal Hypergraph Motifs and Fast Algorithms for Exact Counting
Geon Lee and Kijung Shin
One of the Best-Ranked Papers
[C4] How Do Hyperedges Overlap in Real-World Hypergraphs? — Patterns, Measures, and Generators
Geon Lee*, Minyoung Choe*, and Kijung Shin
2020
[C3] Hypergraph Motifs: Concepts, Algorithms, and Discoveries
Geon Lee, Jihoon Ko, and Kijung Shin
[C2] MEGA: Multi-View Semi-Supervised Clustering of Hypergraphs
Joyce Jiyoung Whang, Rundong Du, Sangwon Jung, Geon Lee, Barry Drake, Qingqing Liu, Seonggoo Kang, and Haesun Park
2019
[C1] Hyperlink Classification via Structured Graph Embedding
Geon Lee, Seonggoo Kang, and Joyce Jiyoung Whang
Academic Service
Conference Reviewer
KDD (2023–2026), AAAI (2024–2026), WWW (2024–2026), ICLR (2025–2026), AISTATS (2025–2026), ICML (2025-2026), NeurIPS (2024–2025), CIKM (2022–2025), LoG (2022–2025), RecSys (2025), ACML (2025), SDM (2024)
Journal Reviewer
TKDE (2023–2026), Information Sciences (2024–2026), TPAMI (2025–2026), IP&M (2025–2026), Scientific Reports (2025-2026), TNNLS (2023–2025), VLDBJ (2023–2025), PLOS ONE (2024–2025), DMKD (2024–2025), TOIS (2025), Neurocomputing (2026), Neural Networks (2025), Machine Learning (2025), TNSE (2024), Patterns (2025), Big Data Research (2024)
Session Chair
CIKM (2024)
Awards & Honors
PhD Dissertation Award Feb 2026
Best Paper Award at ICDM 2025 Dec 2025
One of the Best-Ranked Papers of ICDM 2025 Dec 2025
Best Survey Paper Award at PAKDD 2025 Jun 2025
Outstanding Reviewer of KDD 2025 Dec 2024
KAIST Outstanding Paper Award Nov 2024
Best Short Paper Candidate at RecSys 2024 Oct 2024
One of the Best-Ranked Papers of ICDM 2021 Dec 2021
Sungkyunkwan Presidential Award Aug 2019
Sungkyunkwan Software Scholarship (Full tuition, all semesters) 2016–2019
Teaching
Teaching Assistant
KAIST AI506 — Data Mining and Search Spring 2021, 2023
KAIST AI607 — Graph Mining and Social Network Analysis Fall 2020, 2021, 2022, 2023
KAIST AI617 — Machine Learning for Robotics Spring 2022
SKKU CSE3036 — Seminar in Computer Engineering Fall 2019
Tutorial Tutor
Mining of Real-World Hypergraphs: Patterns, Tools, and Generators CIKM 2022, ICDM 2022, WWW 2023, KDD 2023