非对称信息在链接预测中的应用

针对基于节点相似性的链接关系预测中因未考虑非对称信息导致预测准确度降低的问题，提出一种新的增加非对称信息的节点相似性度量方法。首先，分析了基于共同邻居（CN）的相似性度量算法的缺陷在于仅考虑CN的数量而未考虑各自节点的所有邻居的数量；然后，将节点之间的相似性度量定义为共同节点与所有邻居节点的比值，融合节点间对称相似信息和非对称相似信息，对节点间的相似程度进行深入细致的刻画；最后，将该方法应用到复杂网络中进行链接关系的预测。在真实数据集上的实验结果表明，与目前多种基于共邻的相似性度量方法——CN、AA、资源分配（RA）相比，所提方法提升了节点相似性度量的准确性，并且可以提高复杂网络中链接关系预测的准确度。

Application of asymmetric information in link prediction

The prediction accuracy of link prediction based on node similarity is always reduced without considering the asymmetric information. In order to solve the problem, a novel method for node similarity measurement with asymmetric information was proposed. Firstly, the disadvantage of the similarity measure algorithm based on Common Neighbor (CN) was analyzed, which it only considered the number of CNs without considering the number of all neighbors of each node. Secondly, the similarity measure between nodes was defined as the ratio of the common nodes to all the neighbor nodes. Then, the symmetric similar information and the asymmetric similar information between nodes were combined, and the similarity between nodes was described in detail. Finally, the proposed method was applied to predict the link relationship in complex networks. The experimental results on the real datasets show that, compared with the previous common neighbor-based similarity measurement methods such as CN, Adamic Adar (AA) and Resource Allocation (RA), the proposed method can improve the accuracy of node similarity measurement and improve the accuracy of link relationship prediction in complex networks.