[论文解读] A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications

Hongyun Cai, Vincent W. Zheng+1 more|arXiv (Cornell University)|Sep 22, 2017

Advanced Graph Neural Networks参考文献 133被引用 153

一句话总结

一份全面的综述，定义图嵌入，提出问题设定和技术分类法，综述技术、应用以及图嵌入的未来方向。

ABSTRACT

Graph is an important data representation which appears in a wide diversity of real-world scenarios. Effective graph analytics provides users a deeper understanding of what is behind the data, and thus can benefit a lot of useful applications such as node classification, node recommendation, link prediction, etc. However, most graph analytics methods suffer the high computation and space cost. Graph embedding is an effective yet efficient way to solve the graph analytics problem. It converts the graph data into a low dimensional space in which the graph structural information and graph properties are maximally preserved. In this survey, we conduct a comprehensive review of the literature in graph embedding. We first introduce the formal definition of graph embedding as well as the related concepts. After that, we propose two taxonomies of graph embedding which correspond to what challenges exist in different graph embedding problem settings and how the existing work address these challenges in their solutions. Finally, we summarize the applications that graph embedding enables and suggest four promising future research directions in terms of computation efficiency, problem settings, techniques and application scenarios.

研究动机与目标

• 定义正式的图嵌入概念及输入/输出。
• 提出问题设定和技术分类法以组织文献。
• 总结图嵌入在节点/边/子结构/整个图层面的应用。
• 确定计算、设置、技术和应用四个有前景的未来研究方向。

提出的方法

• 引入图、邻近度度量与嵌入目标的正式定义与记号。
• 给出两种互补的分类法：问题设定（输入/输出）与嵌入技术。
• 系统性分析现有工作在每种设定下如何应对挑战并提取技术背后的潜在见解。
• 将图嵌入应用分类为节点相关、边相关和图相关用例，并给出参考场景。
• 概述四个未来研究方向，并对当前局限性进行批判性分析。

实验结果

研究问题

• RQ1 在不同输入/输出配置下，图嵌入的 canonical 问题设定与挑战是什么？
• RQ2 哪些技术能够应对这些挑战，哪些见解解释了这些技术为何有效？
• RQ3 图嵌入如何支持各类实际应用，未来方向如何推进这一领域？

主要发现

• 两种新颖的分类法通过问题设定与技术对图嵌入研究进行组织。
• 对输入（同质/异质图、具辅助信息的图、由非关系数据构建的图）与输出（节点、边、混合、全图）进行了全面分析。
• 该综述综合了技术并提炼其背后的基本见解，而不仅仅是方法本身。
• 应用被分类为节点相关、边相关和图相关用例，并给出详细场景。
• 四个未来方向强调计算效率、问题设定、技术与应用领域。