Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning
This addresses the challenge of learning from unlabeled heterogeneous graphs, which is common in real-world applications like social networks or knowledge graphs, though it is incremental in improving contrastive learning methods.
The paper tackles the problem of limited labeled data in heterogeneous graphs by proposing a novel contrastive learning framework (ASHGCL) that incorporates node attributes and multi-scale structures, achieving state-of-the-art performance on four real-world datasets and surpassing some supervised benchmarks.
Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. However, in real-world scenarios, labeled data is often difficult to obtain, which limits the applicability of semi-supervised approaches. Self-supervised learning aims to enable models to automatically learn useful features from data, effectively addressing the challenge of limited labeling data. In this paper, we propose a novel contrastive learning framework for heterogeneous graphs (ASHGCL), which incorporates three distinct views, each focusing on node attributes, high-order and low-order structural information, respectively, to effectively capture attribute information, high-order structures, and low-order structures for node representation learning. Furthermore, we introduce an attribute-enhanced positive sample selection strategy that combines both structural information and attribute information, effectively addressing the issue of sampling bias. Extensive experiments on four real-world datasets show that ASHGCL outperforms state-of-the-art unsupervised baselines and even surpasses some supervised benchmarks.