Graph Embedding Techniques, Applications, and Performance: A Survey

By Palash Goyal, Emilio Ferrara. 2017

1,820 citations recorded by the source corpus.

Abstract Graphs, such as social networks, word co-occurrence networks, and communication networks, occur naturally in various real-world applications. Analyzing them yields insight into the structure of society, language, and different patterns of communication. Many approaches have been proposed to perform the analysis. Recently, methods which use the representation of graph nodes in vector space have gained traction from the research community. In this survey, we provide a comprehensive and structured analysis of various graph embedding techniques proposed in the literature. We first introduce the embedding task and its challenges such as scalability, choice of dimensionality, and features to be preserved, and their possible solutions. We then present three categories of approaches based on factorization methods, random walks, and deep learning, with examples of representative algorithms in each category and analysis of their performance on various tasks. We evaluate these state-of-the-art methods on a few common datasets and compare their performance against one another. Our analysis concludes by suggesting some potential applications and future directions. We finally present the open-source Python library we developed, named GEM (Graph Embedding Methods, available at https://github.com/palash1992/GEM ), which provides all presented algorithms within a unified interface to foster and facilitate research on the topic.

Subfields: Artificial Intelligence, Computer Networks and Communications, Statistical and Nonlinear Physics, Representation & Self-Supervised Learning, 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 Representation & Self-Supervised Learning

In Graph Learning

Citations in the corpus

Representation Learning on Graphs: Methods and Applications (2017, methodology): “Thus, instead of using a deterministic measure of graph proximity, like the methods of Section 2.2.1, these random walk methods employ a ﬂexible, stochastic measure of graph proximity, which has led to superior performance in a number of settings [26].”
FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling (2018, background): “Another line of work learns embeddings for graph vertices, for which Goyal & Ferrara (2017) is a recent survey that covers comprehensively several categories of methods.”
Adversarially Regularized Graph Autoencoder (2018, background): “This merit has motivated a number of studies in this area [ Cai et al. , 2017; Goyal and Ferrara, 2017 ] .”
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).”
Simplicial closure and higher-order link prediction (2018, background): “We anticipate that higher-order link prediction will validate emerging higher-order network modeling techniques, such as multipartite networks (49), metapaths (50), and embeddings (51), and connect to ideas in computational topology, such as random walks on simplicial complexes (52, 53).”
Artificial intelligence in cancer target identification and drug discovery (2022, methodology): “For example, graph convolution networks, which have a strong ability of feature representation 177 , can capture the features related to ADMET properties of drugs from their molecular structures.”
Graph Learning: A Survey (2021, background): “to the output prediction results need to be handled by graph learning [21].”
dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning (2018, methodology): “These methods represent each node in the network with a fixed dimensional embedding and map link prediction in the network space to the nearest neighbor search in the embedding space [7].”
An Overview of Deep Semi-Supervised Learning (2020, methodology): “The term graph embedding has been used in the literature in two ways: to represent an entire graph in vector space, or to represent each individual node in vector space [55].”