您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Self-supervised heterogeneous graph neural network based on deep and broad neighborhood encoding

文献类型： 外文期刊

作者： Song, Qianyu 1 ; Li, Chao 1 ; Fu, Jinhu 2 ; Zeng, Qingtian 1 ; Xie, Nengfu 3 ;

作者机构： 1.Shandong Univ Sci & Technol, Coll Elect & Informat Engn, Qingdao 266590, Peoples R China

2.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China

3.Chinese Acad Agr Sci, Minist Agr & Rural Affairs, Agr Informat Inst, Beijing 100081, Peoples R China

关键词： Heterogeneous graphs; Self-supervised learning; Heterogeneous graph neural networks; Graph contrastive learning

期刊名称：APPLIED INTELLIGENCE （ 影响因子：3.5； 五年影响因子：3.8 ）

ISSN： 0924-669X

年卷期： 2025 年 55 卷 7 期

页码：

收录情况： SCI

摘要： Self-supervised heterogeneous graph neural networks have shown remarkable effectiveness in addressing the challenge of limited labeled data. However, current contrastive learning methods face limitations in leveraging neighborhood information for each node. Some approaches utilize the local information of the target node, ignoring useful signals from deeper neighborhoods. On the other hand, simply stacking convolutional layers to expand the neighborhood inevitably leads to over-smoothing. To address the problems, we propose HGNN-DB, a Self-supervised Heterogeneous Graph Neural Network Based on Deep and Broad Neighborhood Encoding to tackle the over-smoothing problem within heterogeneous graphs. Specifically, HGNN-DB aims to learn informative node representations by incorporating both deep and broad neighborhoods. We introduce a deep neighborhood encoder with a distance-weighted strategy to capture deep features of target nodes. Additionally, a single-layer graph convolutional network is employed for the broad neighborhood encoder to aggregate broad features of target nodes. Furthermore, we introduce a collaborative contrastive mechanism to learn the complementarity and potential invariance between the two views of neighborhood information. Experimental results on four real-world datasets and seven baselines demonstrate that our model significantly outperforms the current state-of-the-art techniques on multiple downstream tasks. The codes and datasets for this work are available at https://github.com/SSQiana/HGNN-DB.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台