Graph convolutional networks: a comprehensive review
Сверточные графовые сети: всесторонний обзор
2019-11-10
SCID: 54.1/qt4bdrrp
Discuss with AI
graph convolutional networksgraph neural networksgraph representation learninggraph-structured dataspatial and spectral convolutions
Figures from the paper
Abstract (AI)
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.
Key Findings
1
Graph neural networks, particularly graph convolutional networks (GCNs), have recently demonstrated superior performance on various graph problems.
2
Graphs capture structural relations across domains (social, bioinformatics, computer vision) enabling richer insights than isolated data analysis.
3
Learning low-dimensional representations of graphs can preserve graph properties and help address graph learning challenges.
4
Many traditional graph representation methods are limited by shallow learning mechanisms, motivating deeper models.
5
This survey organizes GCNs by convolution type and application area, and identifies open challenges and future research directions.
Research Object
Graph convolutional networks (GCNs)
Research Subject
Comprehensive review of GCN models, including their convolution types, model categorizations, application areas, limitations, open challenges, and future research directions
Publication Details
Publication Date
2019-11-10
Journal
Publisher
ISSN
Cited by
1885
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
ImageNet classification with deep convolutional neural networks2017
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
Semi-Supervised Classification with Graph Convolutional Networks2016
A Comprehensive Survey on Graph Neural Networks2020
The Graph Neural Network Model2008
Graph neural networks: A review of methods and applications2020
Dynamic Graph CNN for Learning on Point Clouds2019
Neural Message Passing for Quantum Chemistry2017
Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2016
Graph Neural Networks: A Review of Methods and Applications2018
Cited by6
Graph neural networks: A review of methods and applications2020
Deep Learning on Graphs: A Survey2020
Graph Neural Networks: A Review of Methods and Applications2018
Graph Neural Networks for Intelligent Transportation Systems: A Survey2023
Data‐Driven High‐Throughput Rational Design of Double‐Atom Catalysts for Oxygen Evolution and Reduction2022
Graph Neural Networks for Pressure Estimation in Water Distribution Systems2024