I am an Assistant Professor in the Department of Computer Science and Engineering at Seoul National University. Previously, I was a Postdoctoral Fellow at Carnegie Mellon University, where I worked with Leman Akoglu and Christos Faloutsos. My graduate work was supported by the Google PhD Fellowship, the Qualcomm Innovation Fellowship, and the Outstanding Dissertation Award from the Korean Academy of Science and Technology. My research interests cover various topics in data-centric AI, including graph neural networks, time series analysis, recommender systems, and anomaly detection.
I lead the Data AI Lab at Seoul National University and am actively looking for motivated students at all levels. Please visit our group website for more information.
About
2026 — Present
Seoul National University
Assistant Professor, Department of Computer Science and Engineering
Adjunct Professor, Interdisciplinary Program in Artificial Intelligence
Adjunct Professor, Interdisciplinary Program in Artificial Intelligence
2023 — 2026
KAIST (Korea Advanced Institute of Science and Technology)
Assistant Professor, School of Electrical Engineering
Adjunct Professor, Kim Jaechul Graduate School of AI
Adjunct Professor, Kim Jaechul Graduate School of AI
2022 — 2023
Carnegie Mellon University
Postdoctoral Fellow, Heinz College of Information Systems and Public Policy
Advisor: Prof. Leman Akoglu and Prof. Christos Faloutsos
Advisor: Prof. Leman Akoglu and Prof. Christos Faloutsos
2012 — 2022
Seoul National University
Ph.D. and B.S. in Computer Science and Engineering
Thesis: Probabilistic Approaches for Node and Graph Classification
Advisor: Prof. U Kang
Thesis: Probabilistic Approaches for Node and Graph Classification
Advisor: Prof. U Kang
Publications
2026
-
ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation
-
PULSE: Socially-Aware User Representation Modeling Toward Parameter-Efficient Graph Collaborative Filtering
-
Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
2025
-
Simple and Behavior-Driven Augmentation for Recommendation with Rich Collaborative Signals
-
Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
-
'Hello, World!': Making GNNs Talk with LLMs
-
Self-Tuning Self-Supervised Image Anomaly Detection
-
Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
-
Criteria-Aware Graph Filtering: Extremely Fast Yet Accurate Multi-Criteria Recommendation
-
End-To-End Self-Tuning Self-Supervised Time Series Anomaly Detection
2024
-
Rethinking Reconstruction-based Graph-level Anomaly Detectors: Limitations and a Remedy
-
Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
-
NetEffect: Discovery and Exploitation of Generalized Network Effects
-
HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
-
Representative and Back-in-Time Sampling from Real-world Hypergraphs
2023
-
Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities
-
DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection
-
Less is More: SlimG for Accurate, Robust, and Interpretable Graph Mining
-
How Transitive Are Real-World Group Interactions? — Measurement and Reproduction
-
Classification of Edge-dependent Labels of Nodes in Hypergraphs
-
Towards Deep Attention in Graph Neural Networks: Problems and Remedies
-
Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success
-
Reciprocity in Directed Hypergraphs: Measures, Findings, and Generators
2022
-
Accurate Stock Movement Prediction with Self-supervised Learning from Sparse Noisy Tweets
-
Reciprocity in Directed Hypergraphs: Measures, Findings, and Generators
-
Accurate Node Feature Estimation with Structured Variational Graph Autoencoder
-
Model-Agnostic Augmentation for Accurate Graph Classification
-
MiDaS: Representative Sampling from Real-world Hypergraphs
-
Transition Matrix Representation of Trees with Transposed Convolutions
-
Graph-based PU Learning for Binary and Multiclass Classification without Class Prior
-
Signed Random Walk Diffusion for Effective Representation Learning in Signed Graphs
2021
-
Accurate Graph-Based PU Learning without Class Prior★ One of the best-ranked papers of ICDM 2021 for fast-track journal invitation
-
Accurate Multivariate Stock Movement Prediction via Data-Axis Transformer with Multi-Level Contexts
-
Gaussian Soft Decision Trees for Interpretable Feature-Based Classification
-
Attention-Based Autoregression for Accurate and Efficient Multivariate Time Series Forecasting
Before 2021
-
Sampling Subgraphs with Guaranteed Treewidth for Accurate and Efficient Graphical Inference★ Samsung HumanTech Paper Award & Qualcomm Innovation Fellowship Korea
-
Knowledge Extraction with No Observable Data★ Qualcomm Innovation Fellowship Korea
-
EDiT: Interpreting Ensemble Models via Compact Soft Decision Trees
-
Belief Propagation Network for Hard Inductive Semi-Supervised Learning
-
Fast and Scalable Distributed Loopy Belief Propagation on Real-World Graphs
-
Supervised Belief Propagation: Scalable Supervised Inference on Attributed Networks
-
Efficient Learning of Bounded-Treewidth Bayesian Networks from Complete and Incomplete Data Sets
Tutorials
Awards & Honors
- Distinguished PC Member, ECML PKDD 2025 Nov 2025
- S-OIL Outstanding Dissertation Award Dec 2022
- SNU CSE Outstanding Dissertation Award Feb 2022
- One of the Best-Ranked Papers of ICDM 2021 Dec 2021
- SNU BK21 Outstanding Graduate Student Award Jul 2021
- Qualcomm Innovation Fellowship Dec 2020
- Youlchon AI Star Award Sep 2020
- Google PhD Fellowship Sep 2019
- Samsung HumanTech Paper Award Feb 2019
Teaching
- Introduction to Data Mining 2026S
- Foundation of Big Data Analytics 2023F 2024F 2025F
- Programming Structure for Electrical Engineering 2025S
- Introduction to Modern Software Development 2025S
- Discrete Methods for Electrical Engineering 2024S
Professional Service
- Organizer PAKDD GLFM Workshop (2025)
- Area Chair KDD (2026)
- Area Chair NeurIPS (2026)
- Area Chair ICML (2026)
- Senior PC Member CIKM (2025 – 2026)
- Reviewer KDD (2021 – 2026)
- Reviewer WWW (2024 – 2026)
- Reviewer ICLR (2023 – 2026)
- Reviewer ICML (2025)
- Reviewer NeurIPS (2023 – 2025)
- Reviewer AAAI (2021 – 2026)
- Reviewer WSDM (2025 – 2026)
- Reviewer CIKM (2025)
- Reviewer DASFAA (2026)
- Reviewer ECML PKDD (2023 – 2026)
- Reviewer LoG (2022 – 2025)
- Reviewer TMLR (2024 – 2026)