[论文解读] A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources

Xiao Wang, Deyu Bo+4 more|arXiv (Cornell University)|Nov 30, 2020

Advanced Graph Neural Networks被引用 42

一句话总结

本综述全面回顾异质图嵌入方法、分类法、技术、实际部署、数据集和开源工具，强调挑战与未来方向。

ABSTRACT

Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn representations in a lower-dimension space while preserving the heterogeneous structures and semantics for downstream tasks (e.g., node/graph classification, node clustering, link prediction), has drawn considerable attentions in recent years. In this survey, we perform a comprehensive review of the recent development on HG embedding methods and techniques. We first introduce the basic concepts of HG and discuss the unique challenges brought by the heterogeneity for HG embedding in comparison with homogeneous graph representation learning; and then we systemically survey and categorize the state-of-the-art HG embedding methods based on the information they used in the learning process to address the challenges posed by the HG heterogeneity. In particular, for each representative HG embedding method, we provide detailed introduction and further analyze its pros and cons; meanwhile, we also explore the transformativeness and applicability of different types of HG embedding methods in the real-world industrial environments for the first time. In addition, we further present several widely deployed systems that have demonstrated the success of HG embedding techniques in resolving real-world application problems with broader impacts. To facilitate future research and applications in this area, we also summarize the open-source code, existing graph learning platforms and benchmark datasets. Finally, we explore the additional issues and challenges of HG embedding and forecast the future research directions in this field.

研究动机与目标

• 介绍异质图的基本概念，并识别 HG 嵌入所面临的独特挑战
• 按学习中使用的信息系统地对最先进的 HG 嵌入方法进行分类
• 分析 HG 嵌入方法在现实世界场景中的优缺点及其变革性
• 总结开源代码、平台和基准数据集，以促进未来工作
• 讨论异质图嵌入的未解决问题并预测未来方向

提出的方法

• 将 HG 嵌入方法分为结构保持、属性辅助、面向应用和动态方法
• 基于链接、元路径以及如元路径、元图和超边等子图的结构保持方法进行评审
• 讨论基于路径和子图的方法，包括 metapath2vec、metagraph2vec、mg2vec 和 DHNE
• 解释异构属性如何需要融合并影响模型设计
• 强调元路径和元图在捕捉高阶关系中的作用
• 给出用于保留异质性的关系特定度量和学习目标的示例

实验结果

研究问题

• RQ1 与同质图相比，异质性对 HG 嵌入提出的基本挑战是什么？
• RQ2 HG 嵌入方法如何利用不同信息类型（结构、属性、领域知识）来应对这些挑战？
• RQ3 基于链接、路径和子图的 HG 嵌入方法各自的优点与局限性是什么？
• RQ4 HG 嵌入技术如何转化为现实世界的部署和应用？
• RQ5 存在哪些开源资源和基准数据集以支持未来的 HG 嵌入研究？

主要发现

• HG 嵌入方法必须处理复杂的 HG 结构和异质属性，这些与同质图不同
• 基于所使用信息的 HG 嵌入方法存在分类法：结构、属性、应用线索和动态性
• 基于链接、路径和子图的方法在保留异质性方面提供互补的视角，但在复杂性和可扩展性方面存在权衡
• 元路径和元图的概念能够实现高阶语义捕获，而随机游走和混合关系方法提供多样的学习策略
• 若干方法使用关系特定投影、平移距离函数或联合多任务目标来建模异质关系
• 该综述映射了开源代码、平台和基准数据集，以促进未来的 HG 嵌入研究