Generative-Contrastive Heterogeneous Graph Neural Network

arXiv:2404.02810v1 Announce Type: new
Abstract: Heterogeneous Graphs (HGs) can effectively model complex relationships in the real world by multi-type nodes and edges. In recent years, inspired by self-supervised learning, contrastive Heterogeneous Graphs Neural Networks (HGNNs) have shown great potential by utilizing data augmentation and discriminators for downstream tasks. However, data augmentation is still limited due to the discrete and abstract nature of graphs. To tackle the above limitations, we propose a novel \textit{Generative-Contrastive Heterogeneous Graph Neural Network (GC-HGNN)}. Specifically, we …

arxiv cs.ir cs.lg generative graph graph neural network network neural network type