arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.04220cs.SIcs.DS
收藏

探索在线社交网络中的层次结构

Exploring Hierarchies in Online Social Networks

Can Lu, Jeffrey Xu Yu, Rong-Hua Li, Hao Wei

摘要:

社会等级制度(即,社会金字塔结构)是社会学和社会网络分析中的一个基本概念。社会等级在社会网络中的重要性在于,社会等级的拓扑结构在形成个体之间的社会互动的性质和展开社交网络的结构方面都是必不可少的。在社会网络中发现的社会层次结构可以用来提高链接预测的准确性,提供更好的查询结果,排名网页,并研究复杂网络中的信息流动和传播。在本文中,我们将社交网络建模为有向图G,并将社交层次结构视为G的有向无环图(DART),记为GD。通过DAG,G中的所有顶点可以被划分为不同的层,在同一层上的顶点表示社会层次中的不相交组,并且DAG中的所有边都遵循一个方向。本文研究的主要问题是如何在G.我们采用的方法是通过从G中移除所有可能的圈来找到GD,使得G = U(G)+ GD,其中U(G)是包含所有可能圈的最大欧拉子图。我们给出了这样做的原因,研究发现的GD的性质,并讨论了应用。此外,我们开发了一种新的两阶段算法,称为贪婪-&-细化,greetion计算欧拉子图,然后细化这个贪婪的解决方案,找到最大的欧拉子图。我们给出了贪婪解和最优解之间的界。我们贪婪方法的质量很高。我们对14个真实世界的数据集进行了全面的实验研究。结果表明,我们的算法是至少两个数量级的速度比基线算法。

英文摘要:

Social hierarchy (i.e., pyramid structure of societies) is a fundamental concept in sociology and social network analysis. The importance of social hierarchy in a social network is that the topological structure of the social hierarchy is essential in both shaping the nature of social interactions between individuals and unfolding the structure of the social networks. The social hierarchy found in a social network can be utilized to improve the accuracy of link prediction, provide better query results, rank web pages, and study information flow and spread in complex networks. In this paper, we model a social network as a directed graph G, and consider the social hierarchy as DAG (directed acyclic graph) of G, denoted as GD. By DAG, all the vertices in G can be partitioned into different levels, the vertices at the same level represent a disjoint group in the social hierarchy, and all the edges in DAG follow one direction. The main issue we study in this paper is how to find DAG GD in G. The approach we take is to find GD by removing all possible cycles from G such that G = U(G) + GD where U(G) is a maximum Eulerian subgraph which contains all possible cycles. We give the reasons for doing so, investigate the properties of GD found, and discuss the applications. In addition, we develop a novel two-phase algorithm, called Greedy-&-Refine, which greedily computes an Eulerian subgraph and then refines this greedy solution to find the maximum Eulerian subgraph. We give a bound between the greedy solution and the optimal. The quality of our greedy approach is high. We conduct comprehensive experimental studies over 14 real-world datasets. The results show that our algorithms are at least two orders of magnitude faster than the baseline algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑