Node Similarities from Spreading Activation

2010 IEEE International Conference on Data Mining Pub Date : 2010-12-13 DOI:10.1109/ICDM.2010.108

Kilian Thiel, M. Berthold

引用次数: 31

Abstract

In this paper we propose two methods to derive two different kinds of node similarities in a network based on their neighborhood. The first similarity measure focuses on the overlap of direct and indirect neighbors. The second similarity compares nodes based on the structure of their - possibly also very distant - neighborhoods. Instead of using standard node measures, both similarities are derived from spreading activation patterns over time. Whereas in the first method the activation patterns are directly compared, in the second method the relative change of activation over time is compared. We apply both methods to a real-world graph dataset and discuss the results.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

扩散激活的节点相似性

在本文中，我们提出了两种方法来获得网络中两种不同类型的节点相似度。第一种相似性度量侧重于直接邻域和间接邻域的重叠。第二种相似度是根据节点的邻域结构来比较的——也可能是非常遥远的邻域。与使用标准节点度量不同，这两种相似性都是从随着时间的推移而扩展的激活模式中得出的。在第一种方法中，直接比较激活模式，而在第二种方法中，比较激活随时间的相对变化。我们将这两种方法应用于现实世界的图形数据集，并讨论了结果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2010 IEEE International Conference on Data Mining

自引率

0.00%

发文量

期刊最新文献

Generalized Probabilistic Matrix Factorizations for Collaborative Filtering MoodCast: Emotion Prediction via Dynamic Continuous Factor Graph Model Finding Local Anomalies in Very High Dimensional Space Efficient Probabilistic Latent Semantic Analysis with Sparsity Control Enhancing Single-Objective Projective Clustering Ensembles