Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning

Abstract

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.

References in corpus (10)

• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Structural Deep Clustering Network
• Representation Learning for Attributed Multiplex Heterogeneous Network
• MINE: Mutual Information Neural Estimation
• Deep Graph Contrastive Representation Learning
• Information Recovery-Driven Deep Incomplete Multiview Clustering Network
• Multiplex Heterogeneous Graph Convolutional Network
• MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks
• Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
• Incorporating Higher-order Structural Information for Graph Clustering