Hello!

My name is Sunwoo Kim, and I am a Ph.D. student in the Data Mining Lab (advisor: Prof. Kijung Shin) at KAIST AI.

My research interests include

Contact:

Education

Ph.D.

Master

Duration: 03. 2022. ~ 02. 2024.
School: Korea Advanced Institute of Science and Technology (KAIST)
Dept.: Graduate School of Kim Jaechul AI
Advisor: Prof. Kijung Shin
Thesis: How Transitive Are Real-World Group Interactions? - Measurement and Reproduction [KDD 2023]

Bachelor

Tutorial

2025

[C15] 'Hello, World!': Making GNNs Talk with LLMs
- S. Kim, S. Lee, J. Yoo, and K. Shin
- In EMNLP Findings (short)
[C14] A Self-Supervised Mixture-of-Experts Framework for Multi-behavior Recommendation
- K. Kim, S. Kim, G. Lee, and K. Shin
- In CIKM 2025
[C13] Multi-Behavior Recommender Systems: A Survey
- K. Kim, S. Kim, G. Lee, J. Jung, and K. Shin
- In PAKDD 2025 (survey)

2024

[C12] Rethinking Reconstruction-based Graph-level Anomaly Detectors: Limitations and a Simple Remedy.
- S. Kim, S. Lee, F. Bu, S. Kang, K. Kim, J. Yoo, and K. Shin
- In NeurIPS 2024
[C11] Towards Better Utilization of Multiple Views for Bundle Recommendation.
- K. Kim, S. Kim, G. Lee, and K. Shin
- In CIKM 2024 (short)
[C10] A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide.
- S. Kim*, S. Lee*, Y. Gao, A. Antelmi, M. Polato, and K. Shin
- In KDD 2024 (survey)
[C9] SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning.
- J. Lee, S. Kim, and K. Shin
- In KDD 2024
[C8] Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective.
- S. Lee, S. Kim, F. Bu, J. Yoo, J. Tang, and K. Shin.
- In ICML 2024
[C7] Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs.
- L. Liang, S. Kim, K. Shin, Z. Xu, S. Pan, and Y. Qi
- In ICML 2024
[J3] Prototype-Based Explanations for Graph Neural Networks (Extended version of [C1]).
- Y. Shin, S. Kim, and W. Shin
- In TPAMI (Transactions on Pattern Analysis and Machine Intelligence) 2024
[C6] FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer.
- D. Hwang, H. Kim, S. Kim, and K. Shin
- In CVPR 2024
[C5] HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs.
- S. Kim, S. Kang, F. Bu, S. Lee, J. Yoo, and K. Shin.
- In ICLR 2024

2023

[J2] Datasets, tasks, and training methods for large-scale hypergraph learning.
- S. Kim*, D. Lee*, Y. Kim, J. Park, T. Hwang, and K. Shin
- In DAMI (Data Mining and Knowledge Discovery) 2023
- In ECML-PKDD 2023 (journal track paper)
[J1] Reciprocity in Directed Hypergraphs: Measures, Patterns, and Generators (Extended version of [C2]).
- S. Kim, M. Choe, J. Yoo, and K. Shin
- In DAMI (Data Mining and Knowledge Discovery) 2023
[C4] Classification of Edge-dependent Labels of Nodes in Hypergraphs.
- M. Choe, S. Kim, J. Yoo, and K. Shin.
- In KDD 2023
[C3] How Transitive Are Real-World Group Interactions? - Measurement and Reproduction.
- S. Kim, F. Bu, M. Choe, J. Yoo, and K. Shin
- In KDD 2023

2022

[C2] Reciprocity in Directed Hypergraphs: Measures, Patterns, and Generators.
- S. Kim, M. Choe, J. Yoo, and K. Shin.
- In ICDM 2022
[C1] Prototype-Based Explanations for Graph Neural Networks.
- Y. Shin, S. Kim, E. Yoon, and W. Shin.
- In AAAI 2022 (student abstract)

Preprints

[P1] Four-set Hypergraphlets for Characterization of Directed Hypergraphs.
- H. Moon, H. Kim, S. Kim, and K. Shin.

Award

Academic Reviewer

Conference

Journal

Military Service

Project

User-device matching and Household-device matching
- Duration: 04. 2022. ~ 12. 2023.
- Affiliation: Samsung Research

Researcher

Student Researcher
- Duration: 01. 2021. ~ 11. 2021.
- School: Yonsei University (Seoul)
- Dept.: Computational Engineering Science (MIDAS Lab)
- Advisor: Prof. Won Yong Shin

Page updated

Google Sites

Report abuse