A Negative Sample-Free Graph Contrastive Learning Algorithm

Dongming Chen, Mingshuo Nie (), Zhen Wang, Huilin Chen and Dongqi Wang
Additional contact information
Dongming Chen: Software College, Northeastern University, Shenyang 110819, China
Mingshuo Nie: Software College, Northeastern University, Shenyang 110819, China
Zhen Wang: Software College, Northeastern University, Shenyang 110819, China
Huilin Chen: College of Engineering, Computing and Cybernetics, Australian National University, Canberra, ACT 2601, Australia
Dongqi Wang: Software College, Northeastern University, Shenyang 110819, China

Mathematics, 2024, vol. 12, issue 10, 1-16

Abstract: Self-supervised learning is a new machine learning method that does not rely on manually labeled data, and learns from rich unlabeled data itself by designing agent tasks using the input data as supervision to obtain a more generalized representation for application in downstream tasks. However, the current self-supervised learning suffers from the problem of relying on the selection and number of negative samples and the problem of sample bias phenomenon after graph data augmentation. In this paper, we investigate the above problems and propose a corresponding solution, proposing a graph contrastive learning algorithm without negative samples. The model uses matrix sketching in the implicit space for feature augmentation to reduce sample bias and iteratively trains the mutual correlation matrix of two viewpoints by drawing closer to the distance of the constant matrix as the objective function. This method does not require techniques such as negative samples, gradient stopping, and momentum updating to prevent self-supervised model collapse. This method is compared with 10 graph representation learning algorithms on four datasets for node classification tasks, and the experimental results show that the algorithm proposed in this paper achieves good results.

Keywords: complex networks; graph representation learning; self-supervised learning; data augmentation; comparative learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/10/1581/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/10/1581/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:10:p:1581-:d:1397293

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().