Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
This addresses a bottleneck in heterogeneous graph learning for applications like social networks or recommendation systems, though it is an incremental improvement by enhancing existing methods with virtual nodes.
The paper tackles the problem of capturing long-range information in heterogeneous graph neural networks, which often requires many layers and leads to high computational complexity and over-smoothing, by proposing VN-HGCN that uses virtual nodes to achieve effective aggregation with only 4 layers, demonstrating superiority over state-of-the-art baselines on three real-world datasets.
Heterogeneous Graph Neural Networks (HGNNs) have exhibited powerful performance in heterogeneous graph learning by aggregating information from various types of nodes and edges. However, existing heterogeneous graph models often struggle to capture long-range information or necessitate stacking numerous layers to learn such dependencies, resulting in high computational complexity and encountering over-smoothing issues. In this paper, we propose a Virtual Nodes based Heterogeneous Graph Convolutional Network (VN-HGCN), which leverages virtual nodes to facilitate enhanced information flow within the graph. Virtual nodes are auxiliary nodes interconnected with all nodes of a specific type in the graph, facilitating efficient aggregation of long-range information across different types of nodes and edges. By incorporating virtual nodes into the graph structure, VN-HGCN achieves effective information aggregation with only $4$ layers. Additionally, we demonstrate that VN-HGCN can serve as a versatile framework that can be seamlessly applied to other HGNN models, showcasing its generalizability. Empirical evaluations validate the effectiveness of VN-HGCN, and extensive experiments conducted on three real-world heterogeneous graph datasets demonstrate the superiority of our model over several state-of-the-art baselines.