Negative samples selecting strategy for graph contrastive learning

Rui Miao, Yintao Yang, Yao Ma, Xin Juan, Haotian Xue, Jiliang Tang, Ying Wang, Xin Wang

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


Graph neural networks (GNNs) have emerged as a successful method on graph structured data. Limited by expensive labeled data, contrastive learning has been adopted to the graph domain. In most existing node-level graph contrastive learning methods, when applying contrastive learning to a certain unlabeled node (the center node), its corresponding “similar” node (positive sample) is usually generated by data augmentation. Other nodes in the graph are served as the “dissimilar” nodes (negative samples), which leads to two major problems. First, the computational cost can be prohibitively expensive, especially when the graph is large. Second, utilizing some nodes which share the same label with the center node as the negative samples will damage the learning process. Hence, to address these issues, we explore the feasibility of only sampling a part of nodes for graph contrastive learning process. And unlike the previous self-supervised contrastive methods, we use joint training to exploit supervised signals as much as possible in contrastive learning. Hence, we propose a Negative Samples Selecting Strategy to utilize the classification prediction to guide the selection of the negative samples for sampled nodes. Then, we further incorporate this strategy for performing contrastive learning on graphs and propose a framework named Graph Contrastive Learning with Negative Samples Selecting Strategy (GCNSS). We demonstrate that GCNSS can be trained much faster with much less computation memory than graph contrastive learning baselines, and GCNSS can effectively boost the performance of existing GNN models on semi-supervised node classification tasks across many different datasets. The code is in:

Original languageEnglish (US)
Pages (from-to)667-681
Number of pages15
JournalInformation sciences
StatePublished - Oct 2022
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence


  • Contrastive learning
  • Graph neural networks
  • Semi-supervised learning


Dive into the research topics of 'Negative samples selecting strategy for graph contrastive learning'. Together they form a unique fingerprint.

Cite this