3 papers
cs.LG2025
THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation
Ming-Yi Hong, Miao-Chen Chiang, Youchen Teng +3
Heterogeneous Graph Neural Networks (HGNNs) are effective for modeling Heterogeneous Information Networks (HINs), which encode complex multi-typed entities and relations. However,…
cs.LG2024
SynHING: Synthetic Heterogeneous Information Network Generation for Graph Learning and Explanation
Ming-Yi Hong, Yi-Hsiang Huang, Shao-En Lin +3
Graph Neural Networks (GNNs) excel in delineating graph structures in diverse domains, including community analysis and recommendation systems. As the interpretation of GNNs become…
cs.LG2023
A GAN Approach for Node Embedding in Heterogeneous Graphs Using Subgraph Sampling
Hung-Chun Hsu, Bo-Jun Wu, Ming-Yi Hong +2
Graph neural networks (GNNs) face significant challenges with class imbalance, leading to biased inference results. To address this issue in heterogeneous graphs, we propose a nove…