Generative-Contrastive Heterogeneous Graph Neural Network
This work addresses challenges in learning from heterogeneous graph data, which is crucial for applications like social networks and recommendation systems, but it appears incremental as it builds on existing contrastive learning paradigms.
The paper tackles limitations in contrastive learning for heterogeneous graphs, such as limited data augmentation and sampling bias, by proposing a generative-contrastive neural network that enhances contrastive learning with generative methods and hierarchical strategies, achieving state-of-the-art performance on node classification and link prediction tasks across eight datasets.
Heterogeneous Graphs (HGs) effectively model complex relationships in the real world through multi-type nodes and edges. In recent years, inspired by self-supervised learning (SSL), contrastive learning (CL)-based Heterogeneous Graphs Neural Networks (HGNNs) have shown great potential in utilizing data augmentation and contrastive discriminators for downstream tasks. However, data augmentation remains limited due to the graph data's integrity. Furthermore, the contrastive discriminators suffer from sampling bias and lack local heterogeneous information. To tackle the above limitations, we propose a novel Generative-Contrastive Heterogeneous Graph Neural Network (GC-HGNN). Specifically, we propose a heterogeneous graph generative learning method that enhances CL-based paradigm. This paradigm includes: 1) A contrastive view augmentation strategy using a masked autoencoder. 2) Position-aware and semantics-aware positive sample sampling strategy for generating hard negative samples. 3) A hierarchical contrastive learning strategy aimed at capturing local and global information. Furthermore, the hierarchical contrastive learning and sampling strategies aim to constitute an enhanced contrastive discriminator under the generative-contrastive perspective. Finally, we compare our model with seventeen baselines on eight real-world datasets. Our model outperforms the latest baselines on node classification and link prediction tasks.