一种基于改进Logistic模型的链路预测指标融合方法

Hybrid Method for Link Prediction Index Based on Improved Logistic Model

提出一种基于改进Logistic模型的链路预测指标融合方法(HLP),考虑相似性指标预测结果的互补特性以及在不同网络中的重要程度,自适应赋予每个融合相似性指标合理的权重。采用AUC和Precision作为评价指标,在6个真实世界的网络数据集上的实验表明,融合算法的精度均高于所用基准指标。

We propose a hybrid method based on Logistic model. Considering the similarity index of the prediction results of complementary characteristics and importance in different networks, adap- tive fusion gives each index reasonabweight. Experiments on six real-world network datasets show that the AUC and precision of the hybrid method on each target network are higher than those of the baseline.