Scholarlink

<p>Graph contrastive learning has demonstrated success in generating high-quality node representations. Existing data augmentation and pretext tasks for unsupervised graph contrastive learning reslut in suboptimal node representations. In this paper, we propose COIN, a new graph contrastive learning framework with continuous orthogonal augmentation and information balancing, to improve model performance. We introduce a continuous view augmenter with a masked topology module and a cross-channel feature module to adaptively capture both topological and feature information, preventing dimensional collapse. We further propose the InfoBal principle to balance consistency and diversity across views, and to enable effective utilization of representational information. Extensive experiments demonstrate that COIN outperforms state-of-the-art frameworks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

COIN: Graph Contrastive Learning with Orthogonal Continuous Augmentation and Information Balance

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月27日

查看全文
  • Zhenyu Lin,
  • Hongzheng Li,
  • Guanhua Ye,
  • Yawen Li,
  • Meiyu Liang,
  • Yingxia Shao

摘要

Graph contrastive learning has demonstrated success in generating high-quality node representations. Existing data augmentation and pretext tasks for unsupervised graph contrastive learning reslut in suboptimal node representations. In this paper, we propose COIN, a new graph contrastive learning framework with continuous orthogonal augmentation and information balancing, to improve model performance. We introduce a continuous view augmenter with a masked topology module and a cross-channel feature module to adaptively capture both topological and feature information, preventing dimensional collapse. We further propose the InfoBal principle to balance consistency and diversity across views, and to enable effective utilization of representational information. Extensive experiments demonstrate that COIN outperforms state-of-the-art frameworks.