A Comprehensive Survey on Graph Neural Networks
University of Technology Sydney · Monash University · +1 more institution
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
- FWCI
- 534.67
- Percentile
- 100%
- References
- 167
Authors
6- ZWZonghan WuCorresponding
University of Technology Sydney
- SPShirui Pan
Monash University
- FCFengwen Chen
University of Technology Sydney
- GLGuodong Long
University of Technology Sydney
- CZChengqi Zhang
University of Technology Sydney
Topics & keywords
- Deep learning
- Graph
- Convolutional neural network
- Artificial neural network
- Feature learning
- Labeled data
- Training set
- Benchmark (surveying)