FHGE: A Fast Heterogeneous Graph Embedding with Ad-hoc Meta-paths
This addresses a practical bottleneck for deploying heterogeneous graph analysis in real-world scenarios requiring fast ad-hoc queries, though it is incremental as it builds on existing HGNN methods.
The paper tackles the high training costs of heterogeneous graph neural networks (HGNNs) for ad-hoc queries with user-defined meta-paths, proposing FHGE, a fast embedding method that achieves efficient, retraining-free generation of meta-path-guided embeddings, with experiments showing significant advantages in real-time graph analysis.
Graph neural networks (GNNs) have emerged as the state of the art for a variety of graph-related tasks and have been widely used in Heterogeneous Graphs (HetGs), where meta-paths help encode specific semantics between various node types. Despite the revolutionary representation capabilities of existing heterogeneous GNNs (HGNNs) due to their focus on improving the effectiveness of heterogeneity capturing, the huge training costs hinder their practical deployment in real-world scenarios that frequently require handling ad-hoc queries with user-defined meta-paths. To address this, we propose FHGE, a Fast Heterogeneous Graph Embedding designed for efficient, retraining-free generation of meta-path-guided graph embeddings. The key design of the proposed framework is two-fold: segmentation and reconstruction modules. It employs Meta-Path Units (MPUs) to segment the graph into local and global components, enabling swift integration of node embeddings from relevant MPUs during reconstruction and allowing quick adaptation to specific meta-paths. In addition, a dual attention mechanism is applied to enhance semantics capturing. Extensive experiments across diverse datasets demonstrate the effectiveness and efficiency of FHGE in generating meta-path-guided graph embeddings and downstream tasks, such as link prediction and node classification, highlighting its significant advantages for real-time graph analysis in ad-hoc queries.