### Abstract

Graphs naturally appear in numerous application domains, ranging from social analysis, bioinformatics to computer vision. The unique capability of graphs enables capturing the structural relations among data, and thus allows to harvest more insights compared to analyzing data in isolation. However, it is often very challenging to solve the learning problems on graphs, because (1) many types of data are not originally structured as graphs, such as images and text data, and (2) for graph-structured data, the underlying connectivity patterns are often complex and diverse. On the other hand, the representation learning has achieved great successes in many areas. Thereby, a potential solution is to learn the representation of graphs in a low-dimensional Euclidean space, such that the graph properties can be preserved. Although tremendous efforts have been made to address the graph representation learning problem, many of them still suffer from their shallow learning mechanisms. Deep learning models on graphs (e.g., graph neural networks) have recently emerged in machine learning and other related areas, and demonstrated the superior performance in various problems. In this survey, despite numerous types of graph neural networks, we conduct a comprehensive review specifically on the emerging field of graph convolutional networks, which is one of the most prominent graph deep learning models. First, we group the existing graph convolutional network models into two categories based on the types of convolutions and highlight some graph convolutional network models in details. Then, we categorize different graph convolutional networks according to the areas of their applications. Finally, we present several open challenges in this area and discuss potential directions for future research.

Original language | English (US) |
---|---|

Article number | 11 |

Journal | Computational Social Networks |

Volume | 6 |

Issue number | 1 |

DOIs | |

State | Published - Dec 1 2019 |

### Fingerprint

### Keywords

- Aggregation mechanism
- Deep learning
- Graph convolutional networks
- Graph representation learning
- Spatial methods
- Spectral methods

### ASJC Scopus subject areas

- Information Systems
- Modeling and Simulation
- Human-Computer Interaction
- Computer Science Applications

### Cite this

*Computational Social Networks*,

*6*(1), [11]. https://doi.org/10.1186/s40649-019-0069-y

**Graph convolutional networks : a comprehensive review.** / Zhang, Si; Tong, Hanghang; Xu, Jiejun; Maciejewski, Ross.

Research output: Contribution to journal › Article

*Computational Social Networks*, vol. 6, no. 1, 11. https://doi.org/10.1186/s40649-019-0069-y

}

TY - JOUR

T1 - Graph convolutional networks

T2 - a comprehensive review

AU - Zhang, Si

AU - Tong, Hanghang

AU - Xu, Jiejun

AU - Maciejewski, Ross

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Graphs naturally appear in numerous application domains, ranging from social analysis, bioinformatics to computer vision. The unique capability of graphs enables capturing the structural relations among data, and thus allows to harvest more insights compared to analyzing data in isolation. However, it is often very challenging to solve the learning problems on graphs, because (1) many types of data are not originally structured as graphs, such as images and text data, and (2) for graph-structured data, the underlying connectivity patterns are often complex and diverse. On the other hand, the representation learning has achieved great successes in many areas. Thereby, a potential solution is to learn the representation of graphs in a low-dimensional Euclidean space, such that the graph properties can be preserved. Although tremendous efforts have been made to address the graph representation learning problem, many of them still suffer from their shallow learning mechanisms. Deep learning models on graphs (e.g., graph neural networks) have recently emerged in machine learning and other related areas, and demonstrated the superior performance in various problems. In this survey, despite numerous types of graph neural networks, we conduct a comprehensive review specifically on the emerging field of graph convolutional networks, which is one of the most prominent graph deep learning models. First, we group the existing graph convolutional network models into two categories based on the types of convolutions and highlight some graph convolutional network models in details. Then, we categorize different graph convolutional networks according to the areas of their applications. Finally, we present several open challenges in this area and discuss potential directions for future research.

AB - Graphs naturally appear in numerous application domains, ranging from social analysis, bioinformatics to computer vision. The unique capability of graphs enables capturing the structural relations among data, and thus allows to harvest more insights compared to analyzing data in isolation. However, it is often very challenging to solve the learning problems on graphs, because (1) many types of data are not originally structured as graphs, such as images and text data, and (2) for graph-structured data, the underlying connectivity patterns are often complex and diverse. On the other hand, the representation learning has achieved great successes in many areas. Thereby, a potential solution is to learn the representation of graphs in a low-dimensional Euclidean space, such that the graph properties can be preserved. Although tremendous efforts have been made to address the graph representation learning problem, many of them still suffer from their shallow learning mechanisms. Deep learning models on graphs (e.g., graph neural networks) have recently emerged in machine learning and other related areas, and demonstrated the superior performance in various problems. In this survey, despite numerous types of graph neural networks, we conduct a comprehensive review specifically on the emerging field of graph convolutional networks, which is one of the most prominent graph deep learning models. First, we group the existing graph convolutional network models into two categories based on the types of convolutions and highlight some graph convolutional network models in details. Then, we categorize different graph convolutional networks according to the areas of their applications. Finally, we present several open challenges in this area and discuss potential directions for future research.

KW - Aggregation mechanism

KW - Deep learning

KW - Graph convolutional networks

KW - Graph representation learning

KW - Spatial methods

KW - Spectral methods

UR - http://www.scopus.com/inward/record.url?scp=85074681354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074681354&partnerID=8YFLogxK

U2 - 10.1186/s40649-019-0069-y

DO - 10.1186/s40649-019-0069-y

M3 - Article

AN - SCOPUS:85074681354

VL - 6

JO - Computational Social Networks

JF - Computational Social Networks

SN - 2197-4314

IS - 1

M1 - 11

ER -