Back to Search
Start Over
A Good View for Graph Contrastive Learning.
A Good View for Graph Contrastive Learning.
- Source :
-
Entropy . Mar2024, Vol. 26 Issue 3, p208. 18p. - Publication Year :
- 2024
-
Abstract
- Due to the success observed in deep neural networks with contrastive learning, there has been a notable surge in research interest in graph contrastive learning, primarily attributed to its superior performance in graphs with limited labeled data. Within contrastive learning, the selection of a "view" dictates the information captured by the representation, thereby influencing the model's performance. However, assessing the quality of information in these views poses challenges, and determining what constitutes a good view remains unclear. This paper addresses this issue by establishing the definition of a good view through the application of graph information bottleneck and structural entropy theories. Based on theoretical insights, we introduce CtrlGCL, a novel method for achieving a beneficial view in graph contrastive learning through coding tree representation learning. Extensive experiments were conducted to ascertain the effectiveness of the proposed view in unsupervised and semi-supervised learning. In particular, our approach, via CtrlGCL-H, yields an average accuracy enhancement of 1.06% under unsupervised learning when compared to GCL. This improvement underscores the efficacy of our proposed method. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ARTIFICIAL neural networks
*GRAPH algorithms
Subjects
Details
- Language :
- English
- ISSN :
- 10994300
- Volume :
- 26
- Issue :
- 3
- Database :
- Academic Search Index
- Journal :
- Entropy
- Publication Type :
- Academic Journal
- Accession number :
- 176302851
- Full Text :
- https://doi.org/10.3390/e26030208