Abstract

Heterogeneous graphs (HGs) also called heterogeneous information networks (HINs) have become ubiquitous in real-world scenarios. Recently, employing graph neural networks (GNNs) to heterogeneous graphs, known as heterogeneous graph neural networks (HGNNs) which aim to learn embedding in low-dimensional space while preserving heterogeneous structure and semantic for downstream tasks, has drawn considerable attention. This chapter will first give a brief review of the recent development on HG embedding, then introduce typical methods from the perspective of shallow and deep models, especially HGNNs. Finally, it will point out future research directions for HGNNs.

Contents

• Introduction to HGNNs
• Basic Concepts of Heterogeneous Graphs
• Challenges of HG Embedding
• Brief Overview of Current Development
• Shallow Models
• Decomposition-based Methods
• Random Walk-based Models
• Deep Models
• Message Passing-based Methods (HGNNs)
• Encoder-decoder-based Methods
• Adversarial-based Methods
• Review
• Future Directions
• Structures and Properties Preservation
• Deeper Exploration
• Reliability
• Applications

Citation