Jongmin Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jongmin Park has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Sungsu Lim
Chungnam National University, Daejeon, Republic of Korea
4 shared publications - Soohwan Jeong
Department of Computer Science and Engineering, Chungnam National University, Daejeon, Republic of Korea
3 shared publications Byung Suk Lee
1 shared publication- Mingyu Choi
Chungnam National University, Daejeon, Republic of Korea
1 shared publication - Seunghoon Han
Chungnam National University, Daejeon, Republic of Korea
1 shared publication Soohwan Jeong
1 shared publication
Latest Publications
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 561-564
Hyperbolic Heterogeneous Graph Attention Networks
Most previous heterogeneous graph embedding models represent elements in a heterogeneous graph as vector representations in a low-dimensional Euclidean space. However, because heterogeneous graphs inherently possess complex structures, such as hierarchical or power-law structures, distortions can occur when representing them in Euclidean space. To overcome this limitation, we propose Hyperbolic Heterogeneous Graph Attention Networks (HHGAT) that learn vector representations in hyperbolic spaces with metapath instances. We conducted experiments on three real-world heterogeneous graph datasets, demonstrating that HHGAT outperforms state-of-the-art heterogeneous graph embedding models in node classification and clustering tasks. This superior performance is attributed to HHGAT's ability to capture the complex structure of heterogeneous graphs effectively.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 561-564
Open AccessHyperbolic Heterogeneous Graph Attention Networks
Most previous heterogeneous graph embedding models represent elements in a heterogeneous graph as vector representations in a low-dimensional Euclidean space. However, because heterogeneous graphs inherently possess complex structures, such as hierarchical or power-law structures, distortions can occur when representing them in Euclidean space. To overcome this limitation, we propose Hyperbolic Heterogeneous Graph Attention Networks (HHGAT) that learn vector representations in hyperbolic spaces with metapath instances. We conducted experiments on three real-world heterogeneous graph datasets, demonstrating that HHGAT outperforms state-of-the-art heterogeneous graph embedding models in node classification and clustering tasks. This superior performance is attributed to HHGAT's ability to capture the complex structure of heterogeneous graphs effectively.
- 7 November 2023
- Published by Elsevier in Pattern Recognition Letters
- Vol. 176, 140-146
mr2vec: Multiple role-based social network embedding
- 7 November 2023
- Published by Elsevier in Pattern Recognition Letters
- Vol. 176, 140-146
mr2vec: Multiple role-based social network embedding
- 5 August 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 149, 390-401
MIGTNet: Metapath Instance-based Graph Transformation Network for heterogeneous graph embedding
- 5 August 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 149, 390-401
MIGTNet: Metapath Instance-based Graph Transformation Network for heterogeneous graph embedding