Asymmetric Graph Contrastive Learning

Xinglong Chang, Jianrong Wang, Rui Guo, Yingkui Wang () and Weihao Li
Additional contact information
Xinglong Chang: School of New Media and Communication, Tianjin University, Tianjin 300350, China
Jianrong Wang: School of New Media and Communication, Tianjin University, Tianjin 300350, China
Rui Guo: College of Intelligence and Computing, Tianjin University, Tianjin 300350, China
Yingkui Wang: Department of Computer Science and Technology, Tianjin Renai College, Tianjin 301636, China
Weihao Li: Data61-CSIRO, Black Mountain Laboratories, Canberra, ACT 2601, Australia

Mathematics, 2023, vol. 11, issue 21, 1-13

Abstract: Learning effective graph representations in an unsupervised manner is a popular research topic in graph data analysis. Recently, contrastive learning has shown its success in unsupervised graph representation learning. However, how to avoid collapsing solutions for contrastive learning methods remains a critical challenge. In this paper, a simple method is proposed to solve this problem for graph representation learning, which is different from existing commonly used techniques (such as negative samples or predictor network). The proposed model mainly relies on an asymmetric design that consists of two graph neural networks (GNNs) with unequal depth layers to learn node representations from two augmented views and defines contrastive loss only based on positive sample pairs. The simple method has lower computational and memory complexity than existing methods. Furthermore, a theoretical analysis proves that the asymmetric design avoids collapsing solutions when training together with a stop-gradient operation. Our method is compared to nine state-of-the-art methods on six real-world datasets to demonstrate its validity and superiority. The ablation experiments further validated the essential role of the asymmetric architecture.

Keywords: contrastive learning; graph neural networks; graph representation learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/21/4505/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/21/4505/ (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:11:y:2023:i:21:p:4505-:d:1272034

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 ().