• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Joint Conference on Neural Networks >On approximating networks centrality measures via neural learning algorithms
【24h】

On approximating networks centrality measures via neural learning algorithms

机译：通过神经学习算法近似估计网络中心度

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The analysis and study of complex networks are crucial to a number of applications. Vertex centrality measures are an important analysis mechanism to uncover or rank important elements of a given network. However, these metrics have high space and time complexity, which is a severe problem in applications that typically involve large networks. We propose and study the use of neural learning algorithms in such a way that the use of these metrics became feasible in networks of any size. We trained and tested 12 off-the-shelf learning algorithms on several networks. Our results show that the regression output of the machine learning algorithms successfully approximate the real metric values and are a robust alternative in real world applications. We also identified that the model generated by the multilayer layer network trained with the Levenberg-Marquardt algorithm achieved the best performance, both in process time and solution quality, among all the methodologies tested for this task.
机译：复杂网络的分析和研究对于许多应用至关重要。顶点中心度度量是一种重要的分析机制，可用来发现或排名给定网络的重要元素。但是，这些度量标准具有很高的空间和时间复杂性，这在通常涉及大型网络的应用程序中是一个严重的问题。我们提出并研究神经学习算法的使用，以使这些度量的使用在任何规模的网络中都变得可行。我们在多个网络上训练和测试了12种现成的学习算法。我们的结果表明，机器学习算法的回归输出成功地逼近了实际指标值，并且在现实世界的应用中是可靠的替代方案。我们还确定，在为此任务测试的所有方法中，采用Levenberg-Marquardt算法训练的多层网络生成的模型在处理时间和解决方案质量方面均达到了最佳性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号