采用时间度量的半监督链接预测方法

提出了一种采用时间特征的半监督链接预测方法.该方法将链接预测问题视为机器学习中的二类分类问题.针对网络稀疏的问题,方法使用了半监督学习技术,利用网络中大量未连接的节点对辅助已连接节点对进行训练.针对网络中链接动态出现的问题,方法添加了若干时间特征来描述节点对.在现实数据集DBLP和Enron中的实验表明,该方法与未采用时间特征或者未使用半监督技术的链接预测方法相比,均具有更高的预测准确率.

Semi-Supervised Link Prediction Method Using Temporal Metrics

A semi-supervised link prediction method with temporal metrics is presented. In the method, the link prediction is regarded as a binary classification problem in machine learning. Considering the sparsity problem in networks, a semi-supervised learning technique is used to exploit a large number of unlinked node pairs assisting linked node pairs in training process. Considering the network dynamics problem, several temporal metrics are used to describe node pairs. Experimental results in two real datasets DBLP and Enron show that the proposed method has a higher prediction accuracy, compared with the methods without temporal metrics and without semi-supervised learning.