Existing works about link prediction rely mainly on pooling operations which cause loss of edge information or similarity assumptions, so that they are limited in specific networks, and mainly supervised learning methods. We propose a Multi-scale Subgraph Contrastive Learning (MSCL) method. To adapt to networks of different sizes and make direct use of edge information, MSCL converts a sampled subgraph centered on the target link into a line graph as a node-scale to represent links, and mines deep representations by combining two scales information, subgraph-scale and line graph node-scale. After learning the information of the two subgraphs separately by encoders, we use contrastive learning to balance the information of two scales to alleviate the over-reliance of the model on labels and enhance the model’s robustness. MSCL outperforms a set of state-of-the-art graph representation learning solutions on link prediction task in a variety of graphs including biology networks and social networks.

This work was supported by the National Natural Science Foundation of China (61702356), Industry-University Cooperation Education Program of the Ministry of Education, and Shanxi Scholarship Council of China.

Authors and Affiliations

1. College of Information and Computer, Taiyuan University of Technology, Jinzhong, 030600, China

   Shilin Sun, Zehua Zhang, Runze Wang & Hua Tian

Corresponding author

Correspondence toZehua Zhang.

Editors and Affiliations

1. University of Regina, Regina, SK, Canada

   JingTao Yao

2. Iwate Prefectural University, Takizawa, Iwate, Japan

   Hamido Fujita

3. Shanghai University, Shanghai, China

   Xiaodong Yue

4. Tongji University, Shanghai, China

   Duoqian Miao

5. University of Kansas, Lawrence, KS, USA

   Jerzy Grzymala-Busse

6. Soochow University, Suzhou, Jiangsu, China

   Fanzhang Li

Reprints and permissions

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

Policies and ethics