A Survey on Network Embedding

By Peng Cui, Xiao Wang, Jian Pei, Wenwu Zhu. 2017

1,172 citations recorded by the source corpus.

Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the network structure. Recently, a significant amount of progresses have been made toward this emerging network analysis paradigm. In this survey, we focus on categorizing and then reviewing the current development on network embedding methods, and point out its future research directions. We first summarize the motivation of network embedding. We discuss the classical graph embedding algorithms and their relationship with network embedding. Afterwards and primarily, we provide a comprehensive overview of a large number of network embedding methods in a systematic manner, covering the structure- and property-preserving network embedding methods, the network embedding methods with side information, and the advanced information preserving network embedding methods. Moreover, several evaluation approaches for network embedding and some useful online resources, including the network data sets and softwares, are reviewed, too. Finally, we discuss the framework of exploiting these network embedding methods to build an effective system and point out some potential future directions.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

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

1. Philip S. Yu
2. Shirui Pan
3. Chuan Shi
4. Chengqi Zhang
5. Guodong Long
6. Zhiyuan Liu
7. Xiao Wang
8. Jing Jiang

In Statistical and Nonlinear Physics

1. Chuan Shi
2. Shirui Pan
3. Chengqi Zhang
4. Xiao Wang
5. Guodong Long
6. Philip S. Yu
7. Jing Jiang
8. Ruiqi Hu

Citations in the corpus

• Adversarially Regularized Graph Autoencoder (2018, background): “However, the high computational complexity, low parallelizability, and inapplicability of machine learning methods to graph data have made these graph analytic tasks profoundly challenging [Cui et al., 2017].”
• Learning Graph Embedding With Adversarial Training Methods (2019, neutral): “graph-analytic tasks profoundly challenging [8], [9].”
• A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, background): “The more recent studies, such as deep graph representation learning and graph neural networks (GNNs), further enrich the capability of deep learning for graph data mining [58], [59], [60], [61], [62].”
• A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, neutral): “One basic requirement of graph embedding is to preserve the graph structures properly [14].”
• Representation Learning for Dynamic Graphs: A Survey (2019, background): “Note that there are already many good surveys on static graphs (see, e.g., Hamilton et al. (2017b); Zhang et al. (2018b); Cai et al. (2018); Cui et al. (2018); Nickel et al. (2016a); Shi et al. (2016); Wang et al. (2017a)).”
• Dynamic Network Embedding : An Extended Approach for Skip-gram based Network Embedding (2018, methodology): “Network embedding can be categorized into the structure-preserving methods and property-preserving methods [Cui et al. , 2017].”
• Deep Learning on Graphs: A Survey (2018, neutral): “Another closely related topic is network embedding, aiming to embed nodes into a low-dimensional vector space [15], [16], [17].”
• Heterogeneous Graph Neural Network (2019, background): “Graph representation learning [3] has became one of the most popular data mining topics in the past few years.”
• Graph Neural Networks: A Review of Methods and Applications (2018, background): “an domain to non-Euclidean domain. Fig. 1. Left: image in Euclidean space. Right: graph in non-Euclidean space arXiv:1812.08434v4 [cs.LG] 10 Jul 2019 2 The other motivation comes from graph embedding [11]– [15], which learns to represent graph nodes, edges or subgraphs in low-dimensional vectors. In”
• Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “Note that there are already many good surveys on static graphs [88, 251, 27, 48, 172, 227].”
• Heterogeneous Information Network Embedding for Recommendation (2017, methodology): “On the other hand, network embedding has shown its potential in structure feature extraction and has been successfully applied in many data mining tasks [39], [40], [41], [42], such as classification [43], clustering [44], [45] and recommendation [46], [47].”
• GMAN: A Graph Multi-Attention Network for Traffic Prediction (2019, background): “Another line of studies focus on graph embedding, which learns low-dimensional representations for vertices that preserve the graph structure information (Grover and Leskovec 2016; Cui et al. 2019).”
• Heterogeneous Graph Attention Network (2019, methodology): “thods [36], the matrix factorization based methods [22, 37], and others, e.g., LINE [33]. However, all these algorithms are proposed for the homogeneous graphs. Some elaborate reviews can be found in [5, 11]. Heterogeneous graph embedding mainly focuses on preserving the meta-path based structural i”
• Evolutionary Architecture Search for Graph Neural Networks (2020, background): “NETWORK data and systems are ubiquitous [1], [2] in the real world including social network, document”
• AutoGraph: Automated Graph Neural Network (2020, methodology): “N models for different tasks efficiently. – The GNN models generated by our method can outperform the handcrafted state-ofthe-art GNN models. 2 Related Work Inspired by CNNs [10,9] and graph embedding [2,4], GNNs are proposed to collectively aggregate information from graph structure. It is first prop”
• EKT: Exercise-Aware Knowledge Tracing for Student Performance Prediction (2019, neutral): “language processing [36], network embedding [37], [38], and also educational applications like question difficulty prediction [39], some researchers attempted to use deep models for”