A Comprehensive Survey on Graph Neural Networks

ZWZonghan WuSPShirui PanFCFengwen ChenGLGuodong LongCZChengqi Zhang

University of Technology Sydney · Monash University · +1 more institution

PubMed
Indexed inarxivcrossrefpubmed

Abstract

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview…

Citation impact

9,040
total citations
FWCI
534.67
Percentile
100%
References
167
Citations per year

Authors

6
  • ZW
    Zonghan WuCorresponding

    University of Technology Sydney

  • SP
    Shirui Pan

    Monash University

  • FC
    Fengwen Chen

    University of Technology Sydney

  • GL
    Guodong Long

    University of Technology Sydney

  • CZ
    Chengqi Zhang

    University of Technology Sydney

Topics & keywords

Keywords
  • Deep learning
  • Graph
  • Convolutional neural network
  • Artificial neural network
  • Feature learning
  • Labeled data
  • Training set
  • Benchmark (surveying)
No related works found for this paper.

Funding