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 first propose a heterogeneous
graph generative learning enhanced contrastive paradigm. This paradigm
includes: 1) A contrastive view augmentation strategy by using masked
autoencoder. 2) Position-aware and semantics-aware positive sample sampling
strategy for generate hard negative samples. 3) A hierarchical contrastive
learning strategy for capturing local and global information. Furthermore, the
hierarchical contrastive learning and sampling strategies aim to constitute an
enhanced discriminator under the generative-contrastive perspective. Finally,
we compare our model with seventeen baselines on eight real-world datasets. Our
model outperforms the latest contrastive and generative baselines on node
classification and link prediction tasks. To reproduce our work, we have
open-sourced our code at this https URL

通过利用自监督学习，我们提出了一种新颖的生成对比异构图神经网络 (GC-HGNN)，并且在结点分类和链接预测任务中显著超越最新的对比和生成基线模型。