Junhyun Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junhyun Lee has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jaewoo Kang
Korea University
3 shared publications Bumsoo Kim
LG AI Research, Seoul, South Korea
1 shared publication- Bumsoo Kim
Graduate School of Applied Art and Technology, Chung-Ang University, Anseong-si 17546, Republic of Korea
1 shared publication - Minji Jeon
Korea University College of Medicine 73 Goryeodae-ro
1 shared publication - Tengfei Ma
Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York, USA
1 shared publication - Veronika Thost
MIT-IBM Watson AI Lab IBM Research
1 shared publication
Latest Publications
- 19 April 2026
- Published by Elsevier in Information Sciences
- Vol. 749
Subgraph-level universal prompt tuning
- 19 April 2026
- Published by Elsevier in Information Sciences
- Vol. 749
Subgraph-level universal prompt tuning
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1253-1261
Understanding and Tackling Over-Dilution in Graph Neural Networks
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1253-1261
Open AccessUnderstanding and Tackling Over-Dilution in Graph Neural Networks
- Open Access
- 27 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 78549-78560
Co-Attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
Graph Neural Networks (GNNs) have proven to be effective in processing and learning from graph-structured data. However, many real-world tasks require the analysis of pairs of graph-structured data, such as scene graph matching, code search, and drug-drug interaction prediction. Previous approaches for considering the interaction between these pairs of graphs have focused on the node level, leading to high computational costs and suboptimal performance. To address this issue, we propose a novel, efficient graph-level approach for extracting interaction representation using co-attention in graph pooling. Our method, Co-Attention Graph Pooling (CAGPool), shows competitive performance compared to existing methods on both classification and regression tasks on real-world datasets, while maintaining low computational complexity.
- 27 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 78549-78560
Open AccessCo-Attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
Graph Neural Networks (GNNs) have proven to be effective in processing and learning from graph-structured data. However, many real-world tasks require the analysis of pairs of graph-structured data, such as scene graph matching, code search, and drug-drug interaction prediction. Previous approaches for considering the interaction between these pairs of graphs have focused on the node level, leading to high computational costs and suboptimal performance. To address this issue, we propose a novel, efficient graph-level approach for extracting interaction representation using co-attention in graph pooling. Our method, Co-Attention Graph Pooling (CAGPool), shows competitive performance compared to existing methods on both classification and regression tasks on real-world datasets, while maintaining low computational complexity.