Scholar
Dongkwan Kim
Google Scholar ID: KgjSE64AAAAJ
Texas A&M University
Citations & Impact
Citations
451
H-index
6
i10-index
5
Publications
12
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- Selected publications include 'Generalizing Weisfeiler-Lehman Kernels to Subgraphs' (ICLR 2025), 'Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning' (ICML 2024), etc. He has also served as a reviewer for several international conferences and organized academic workshops.
Research Experience
- During his Ph.D. at KAIST School of Computing, he studied representation learning for structured data, focusing on the intersection of graph neural networks (GNNs) and large language models (LLMs). His Ph.D. research contributed to graph representation learning methods that leverage pairwise and higher-order interactions for graph-structured data.
Education
- Ph.D. in School of Computing, KAIST, Aug 2025, Advisor: Prof. Alice Oh; M.S. in School of Computing, KAIST, Aug 2019; B.S. in Computer Science and Minor in Chemistry, KAIST, Feb 2018.
Background
- Postdoctoral Researcher at Texas A&M University, working with Prof. Yang Shen. His research aims to build foundational models for biology and chemistry that understand and integrate multiple data modalities such as graphs and texts. The goal of his work is to accelerate scientific discovery by enabling AI systems to reason over complex relational and hierarchical structures found in biological, chemical, and biomedical domains.
Miscellany
- He has extensive teaching experience, having served as a teaching assistant for courses such as Data Structures, Machine Learning for Natural Language Processing, and Deep Learning for Real-world Problems, and has received Best TA Awards.
