A local random walk model for complex networks based on discriminative feature combinations

作者：

Highlights：

• A local random walk model based on discriminative feature combinations is proposed.

• Selecting discriminative feature combinations can improve predictive models.

• Combining attributes and topology structures can improve link-prediction results.

摘要

•A local random walk model based on discriminative feature combinations is proposed.•Selecting discriminative feature combinations can improve predictive models.•Combining attributes and topology structures can improve link-prediction results.

论文关键词：Link prediction,Local random walk,Discriminative feature combination,The strength of feature combination,Probability transfer matrix

论文评审过程：Received 14 November 2017, Revised 9 October 2018, Accepted 10 October 2018, Available online 10 October 2018, Version of Record 16 October 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.10.018