.png){kind=icon}
Return
Graph Self-Supervised Learning: A Survey
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2022.3172903.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field.
Keywords:
Task analysis
Manuals
Supervised learning
Taxonomy
Natural language processing
Data models
Deep learning
Self-supervised learning
graph analytics
deep learning
graph representation learning
graph neural networks
Journal
IF:
10.4
Papers:
6.9K
Citations:
3.2W
Organization
Cited Papers
Patterns of sexual, bilateral and interpopulational variation in human femoral neck‐shaft angles
OAAI
.png){kind=icon}
OAAIShareSaveShareSaveInsurance activity and economic performance: Fresh evidence from asymmetric panel causality testsOAAI
OAAIShareSave
View more