【摘要】 研究社会网络中边的链接预测问题,试图根据网络中边的结构权重信息,将无权网络转换为加权网络进行研究。进而,对于一些加权网络,重新考虑其权重,分别以真实权重、结构权重以及将两者结合后的值作为网络中边的权重,研究resource allocation along local path(RALP)等指标、资源分配(RA)指标和局部路径(LP)指标在加权网络中的链接预测情况。实验结果表明,文中所提统计方法有着良好的预测效果,而且加权RALP指标的预测精度优于加权RA指标和加权LP指标。更多还原

【Abstract】 In this paper,we try to study the link prediction problem of social network by treating the structure information as a transform function and transforming un-weighted network to weighted one. Further,for some weighted networks,we rethink their weights,and consider the real weights、structure weights as well as the combination of these two values as the weight of these networks respectively and study the link prediction problem of resource allocation along local path、resource allocation index and local path index in weighted networks. The experiments show that statistical method in structure weight-based networks has a well prediction effect. Simultaneously,weighted RALP also performs better than both the weighted RA and weighted LP.更多还原