Graph convolutional networks: a comprehensive review

By Si Zhang, Hanghang Tong, Jiejun Xu, Ross Maciejewski. Computational Social Networks, 2019

1,801 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/d474bf3cac3f3824778dbc494bd2e89f6f8e57dc

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 Vision and Pattern Recognition

In Statistical and Nonlinear Physics

Citations in the corpus

A Gentle Introduction to Deep Learning for Graphs (2019, background): “Lastly, a certain number of survey papers have started to appear in the literature [7, 19, 48, 55, 144, 130, 143], while a more slowly-paced introduction to the methodology seems lacking.”
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation (2023, background): “Some works [24, 26, 43] built graphs consisting of attributes and objects, of which relationship is learnt by graph neural networks [52].”
Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence (2023, methodology): “With the help of artifcial intelligence technologies such as deep learning and reinforcement learning, GCN can quickly mine topological information and complex features in graph structures and have solved many major problems in the felds of computer vision, recommendation systems, and knowledge grap”
Predicting the Future from First Person (Egocentric) Vision: A Survey (2021, background): “It is also worth noticing that current trends in deep learning, such as using attention mechanisms instead of recurrent models for sequence modelling [145], or graph convolutional networks [154], gave inspiration to state-of-the-art models [53, 120].”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, background): “Zhang et al. [18] presented one of the first surveys on GNNs, but focused only on graph convolutional neural networks (GCNs).”
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs (2020, background): “Besides the models mentioned above, there are various comprehensive reviews describing previously proposed architectures [42, 5, 41].”