Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Lattice Centering and Coordination Number02:33

Lattice Centering and Coordination Number

10.0K
The structure of a crystalline solid, whether a metal or not, is best described by considering its simplest repeating unit, which is referred to as its unit cell. The unit cell consists of lattice points that represent the locations of atoms or ions. The entire structure then consists of this unit cell repeating in three dimensions. The three different types of unit cells present in the cubic lattice are illustrated in Figure 1.
Types of Unit Cells
Imagine taking a large number of identical...
10.0K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

DNMT3B aggravated renal fibrosis in diabetic kidney disease via activating Wnt/β-catenin signaling pathway.

Scientific reports·2025
Same author

Correction: Galactin-8 DNA methylation mediates macrophage autophagy through the MAPK/mTOR pathway to alleviate atherosclerosis.

Scientific reports·2025
Same author

Overcoming barriers in glioblastoma: The potential of CAR T cell immunotherapy.

Theranostics·2025
Same author

Associations of ambient air pollution exposure and sleep pattern with brain structures: A prospective study in the UK Biobank.

Ecotoxicology and environmental safety·2025
Same author

Relationship between resilience and social trust in nursing homes in Guangzhou, China: a cross-sectional study.

BMJ open·2025
Same author

Aptasensing Technology and Its Potential Applications: Where Do We Stand?

Molecular pharmaceutics·2025

相关实验视频

Updated: Sep 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

650

基于GCN的无监督社区检测,精细的结构中心和扩展的伪标签集.

Bing Guo1, Liping Deng2, Tao Lian3

  • 1Department of Computer Science and Technology, Taiyuan Normal University, Jinzhong, Shanxi, China.

PloS one
|July 1, 2025
PubMed
概括

本研究介绍了RE-GCN,这是一种用于无监督社区检测的新型图形卷积网络 (GCN) 方法. 它改进了结构中心,并扩展了伪标签集,以改进图形分析和社区发现.

更多相关视频

Super-resolution Imaging of Neuronal Dense-core Vesicles
09:30

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

9.8K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K

相关实验视频

Last Updated: Sep 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

650
Super-resolution Imaging of Neuronal Dense-core Vesicles
09:30

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

9.8K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K

科学领域:

  • 图形理论是指图形的理论.
  • 网络分析 网络分析
  • 机器学习 机器学习

背景情况:

  • 社区检测对于理解图形结构数据至关重要.
  • 图形卷积网络 (GCN) 提供无监督的社区检测,但严重依赖初始中心,并且标签传播有限.
  • 浅层GCN由于局部过而难以在整个图表中传播有限的标签信息.

研究的目的:

  • 开发一种改进的基于GCN的无监督社区检测方法 (RE-GCN).
  • 为了解决GCN对初始结构中心的敏感性.
  • 提高浅层GCN的标签传播能力,以便更有效地检测社区.

主要方法:

  • RE-GCN通过交替在GCN分区和更新中心之间根据子图的重要性来代地改进结构中心.
  • 它通过选择具有与其结构中心相似的关联强度的节点来扩展伪标签集.
  • 该方法整合了网络拓和节点属性,用于社区检测.

主要成果:

  • 改进过程产生了更多具有代表性的结构中心.
  • 扩大伪标签集显著提高了GCN在社区检测中的性能.
  • 在赋值和非赋值网络上,RE-GCN表现出有效性.

结论:

  • RE-GCN通过完善结构中心和扩大伪标签数据,为无监督社区检测提供了强大的方法.
  • 该方法克服了传统GCN在处理初始中心灵敏度和标签传播方面的局限性.
  • 拟议的技术提高了复杂网络中社区检测的准确性和可靠性.