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
Representation learning on (hyper)graphs
Self-supervised representation learning
Mining patterns of real-world complex networks
Contact:
Education
Ph.D.
Duration: 03. 2024. ~ ING
School: Korea Advanced Institute of Science and Technology (KAIST)
Dept.: Graduate School of Kim Jaechul AI
Advisor: Prof. Kijung Shin
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
Duration: 03. 2016. ~ 02. 2022.
School: Yonsei University (Seoul)
Major: Applied Statistics (GPA: 4.1/4.3)
Publications & Lectures
Tutorial
[T1] S. Kim*, S. Lee*, Y. Gao, A. Antelmi, M. Polato, and K. Shin. Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide. In KDD 2024 (Lecture-style tutorial)
Preprints
[P1] H. Moon, H. Kim, S. Kim, and K. Shin. Four-set Hypergraphlets for Characterization of Directed Hypergraphs. 2023
2024
[C10] S. Kim*, S. Lee*, Y. Gao, A. Antelmi, M. Polato, and K. Shin. A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide. In KDD 2024 (survey paper)
[C9] J. Lee, S. Kim, and K. Shin. SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning. In KDD 2024
[C8] S. Lee, S. Kim, F. Bu, J. Yoo, J. Tang, and K. Shin. Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective. In ICML 2024
[C7] L. Liang, S. Kim, K. Shin, Z. Xu, S. Pan, and Y. Qi. Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs. In ICML 2024
[J3] Y. Shin, S. Kim, and W. Shin. Prototype-Based Explanations for Graph Neural Networks (Extended version of [C1]). In TPAMI (Transactions on Pattern Analysis and Machine Intelligence) 2024
[C6] D. Hwang, H. Kim, S. Kim, and K. Shin. FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer. In CVPR 2024
[C5] S. Kim, S. Kang, F. Bu, S. Lee, J. Yoo, and K. Shin. HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs. In ICLR 2024
2023
[J2] S. Kim*, D. Lee*, Y. Kim, J. Park, T. Hwang, and K. Shin. Datasets, tasks, and training methods for large-scale hypergraph learning. In DAMI (Data Mining and Knowledge Discovery) 2023
[J1] S. Kim, M. Choe, J. Yoo, and K. Shin. Reciprocity in Directed Hypergraphs: Measures, Patterns, and Generators (Extended version of [C2]). In DAMI (Data Mining and Knowledge Discovery) 2023
[C4] M. Choe, S. Kim, J. Yoo, and K. Shin. Classification of Edge-dependent Labels of Nodes in Hypergraphs. In KDD 2023
[C3] S. Kim, F. Bu, M. Choe, J. Yoo, and K. Shin. How Transitive Are Real-World Group Interactions? - Measurement and Reproduction. In KDD 2023
2022
[C2] S. Kim, M. Choe, J. Yoo, and K. Shin. Reciprocity in Directed Hypergraphs: Measures, Patterns, and Generators. In ICDM 2022
[C1] Y. Shin, S. Kim, E. Yoon, and W. Shin. Prototype-Based Explanations for Graph Neural Networks (Student Abstract). In AAAI 2022 (Student Abstract Track)
Experience
Academic Reviewer
NeurIPS 2024
KDD 2024
Military Service
Duration: 09. 2017. ~ 05. 2019
Division: 2nd (currently 12th) Infantry Division of the Republic Of Korea Army
Role: Information soldier
Rank: Sergeant
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