A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications

By Hongyun Cai, Vincent Wenchen Zheng, Kevin Chen-Chuan Chang. 2017

1,965 citations recorded by the source corpus.

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 maximumly 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 addresses 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.

Subfields: Artificial Intelligence, Computer Networks and Communications, Statistical and Nonlinear Physics, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Statistical and Nonlinear Physics

In Graph Learning

Citations in the corpus

Graph Convolutional Networks for Text Classification (2018, methodology): “Possible solutions to the problem are introducing inductive (Hamilton, Ying, and Leskovec 2017) or fast GCN model (Chen, Ma, and Xiao 2018).”
Compositional Fairness Constraints for Graph Embeddings (2019, background): “In more recent years, the task of embedding graph-structured data has received increasing attention from the machine learning and data mining communities (Cai et al., 2018; Hamilton et al., 2017b).”
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (2017, background): “For a comprehensive recent survey see Cai et al. (2017), Hamilton et al. (2017), or Goyal & Ferrara (2017).”
Embedding Temporal Network via Neighborhood Formation (2018, background): “Network embedding, also known as graph embedding or graph representation learning, aims to find a low-dimensional vector space that can maximumly preserve the original network structural information and network properties [4].”
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks (2020, background): “Here, we first introduce the definition of basic concepts of graph embedding and knowledge graph based on [24], [76].”
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, neutral): “different from the existing surveys which mainly focus on homogeneous graph embedding [14], [27], [28], [29], [30], [31], we aim at exploring the works on heterogeneous graph”
GraphSAINT: Graph Sampling Based Inductive Learning Method (2019, methodology): “Recently, representation learning on graphs has attracted much attention, since it greatly facilitates tasks such as classiﬁcation and clustering (Wu et al., 2019; Cai et al., 2017).”
Taking Human out of Learning Applications: A Survey on Automated Machine Learning (2018, background): “For example, graph embedding [162], active learning [163], and semi-supervised learning [164].”
E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT (2021, background): “Node embedding is typically a key precursor to apply for downstream tasks such as node classification and node clustering [17].”
Convolutional Neural Network Architectures for Signals Supported on Graphs (2018, methodology): “Transforming graph data is the main concern of graph embeddings [33].”
Representation Learning for Dynamic Graphs: A Survey (2019, background): “Other formulations for the transform function can be found in several recent surveys (see, e.g., Zhou et al. (2018a); Cai et al. (2018)).”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, background): “Other formulations for the transform function can be found in several recent surveys (see, e.g., [256, 27]).”
Revisiting User Mobility and Social Relationships in LBSNs: A Hypergraph Embedding Approach (2019, methodology): “When applied to networks or graphs, this paradigm is typically known as graph (or network) embedding [5], which represents nodes”
Combining Graph Neural Networks With Expert Knowledge for Smart Contract Vulnerability Detection (2021, background): “With the remarkable success of neural networks, graph neural network has been investigated extensively in various fields such as graph classification [32], [33], program analysis [34], [35], and graph embedding [36].”
Topological Recurrent Neural Network for Diffusion Prediction (2017, background): “A comprehensive survey of graph embedding with different types of outputs is in [40].”