Graph Self-Supervised Learning: A Survey

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), w...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on knowledge and data engineering Ročník 35; číslo 6; s. 5879 - 5900
Hlavní autoři: Liu, Yixin, Jin, Ming, Pan, Shirui, Zhou, Chuan, Zheng, Yu, Xia, Feng, Yu, Philip S.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.06.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Computer vision
Data models
Deep learning
graph analytics
graph neural networks
graph representation learning
Graphs
Manuals
Natural language processing
Robustness (mathematics)
Self-supervised learning
Supervised learning
Task analysis
Taxonomy
ISSN:1041-4347, 1558-2191
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2022.3172903