FHGE: A Fast Heterogeneous Graph Embedding with Ad-hoc Meta-paths

2025-02-22

AI Summary

Existing heterogeneous graph neural networks (HGNNs) exhibit strong representational capacity but require costly retraining for ad-hoc queries defined by user-specified meta-paths, hindering real-time analytical applications. To address this, we propose MPU-Net, a training-free, fast meta-path embedding framework. MPU-Net introduces the Meta-Path Unit (MPU)—a novel split-reconstruct architecture that decomposes arbitrary meta-paths into reusable atomic units. It integrates local-global graph partitioning, a differentiable reconstruction module, and a two-level attention fusion mechanism to enable zero-shot adaptation to unseen meta-paths without retraining. Evaluated on multi-source heterogeneous graphs, MPU-Net accelerates embedding generation by 5.2–11.8× over state-of-the-art methods, while maintaining or surpassing their accuracy on downstream tasks—including link prediction and node classification. Crucially, it supports millisecond-level ad-hoc querying, enabling real-time, flexible meta-path analytics.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

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.

Problem

• Efficient heterogeneous graph embedding
• Handling ad-hoc meta-paths
• Reducing training costs

Innovation

• Fast Heterogeneous Graph Embedding
• Meta-Path Units segmentation
• Dual attention mechanism