Heterogeneous Graph Neural Network with Multi-view Representation Learning
This work addresses the challenge of generating comprehensive node embeddings for heterogeneous graphs, which is important for applications like social networks and recommendation systems, but it appears incremental as it builds on existing GNN methods with multi-view learning.
The paper tackles the problem of insufficient modeling of local structure and heterogeneity in heterogeneous graph embedding by proposing MV-HetGNN, which uses multi-view representation learning to integrate complex structural and semantic information, resulting in consistent outperformance over state-of-the-art GNN baselines in node classification, clustering, and link prediction tasks on three real-world datasets.
Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph. However, on the one hand, most of existing heterogeneous graph embedding methods either insufficiently model the local structure under specific semantic, or neglect the heterogeneity when aggregating information from it. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain versatile node embeddings. To address the problem, we propose a Heterogeneous Graph Neural Network with Multi-View Representation Learning (named MV-HetGNN) for heterogeneous graph embedding by introducing the idea of multi-view representation learning. The proposed model consists of node feature transformation, view-specific ego graph encoding and auto multi-view fusion to thoroughly learn complex structural and semantic information for generating comprehensive node representations. Extensive experiments on three real-world heterogeneous graph datasets show that the proposed MV-HetGNN model consistently outperforms all the state-of-the-art GNN baselines in various downstream tasks, e.g., node classification, node clustering, and link prediction.