Heterogeneous Graph Contrastive Learning With Augmentation Graph
- 17 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (10) , 5100-5109
Abstract
Heterogeneous graph neural networks (HGNNs) have demonstrated promising capabilities in addressing various problems defined on heterogeneous graphs containing multiple types of nodes or edges. However, traditional HGNN models depend on label information and capture the local structural information of the original graph. In this paper, we propose a novel Heterogeneous Graph Contrastive Learning method with Augmentation Graph (AHGCL). Specifically, we construct an augmentation graph by calculating the feature similarity of nodes to capture latent structural information. For the original graph and the augmentation graph, we employ a shared Graph Neural Network (GNN) encoder to extract the semantic features of nodes with different meta-paths. The feature information is aggregated through a semantic-level attention mechanism to generate final node embeddings, which capture latent high-order semantic structural information. Considering the problems of label information for the real-world datasets, we adopt contrastive learning to train the GNN encoder for maximizing the common information between similar nodes from the original graph and the augmentation graph views. We conduct node classification experiments on four real-world datasets, AMiner, Freebase, DBLP, and ACM, to evaluate the performance of AHGCL. The results show that the proposed AHGCL demonstrates excellent stability and capability compared to existing graph representation learning methods.Keywords
Funding Information
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China (22KJD120002)
This publication has 28 references indexed in Scilit:
- Multimodal graph learning based on 3D Haar semi-tight framelet for student engagement predictionInformation Fusion, 2024
- BLoG: Bootstrapped graph representation learning with local and global regularization for recommendationPattern Recognition, 2023
- Self-supervised contrastive learning on heterogeneous graphs with mutual constraints of structure and featureInformation Sciences, 2023
- Graph attention network via node similarity for link predictionThe European Physical Journal B, 2023
- HGBER: Heterogeneous Graph Neural Network With Bidirectional Encoding RepresentationIEEE Transactions on Neural Networks and Learning Systems, 2023
- Are Graph Convolutional Networks With Random Weights Feasible?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Self-Supervised Learning of Graph Neural Networks: A Unified ReviewIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks2021
- Predicting drug-disease associations with heterogeneous network embeddingChaos: An Interdisciplinary Journal of Nonlinear Science, 2019
- Co-author Relationship Prediction in Heterogeneous Bibliographic Networks2011