Evidential link prediction by exploiting the applicability of similarity indexes to nodes

作者：

Highlights：

• A new hybrid algorithm is proposed to solve the link prediction problem.

• The proposed method combines multiple similarity indexes via the evidence theory.

• The applicable coefficient of an index to a node is defined.

• Experiments show the proposed method achieves superior performance.

摘要

•A new hybrid algorithm is proposed to solve the link prediction problem.•The proposed method combines multiple similarity indexes via the evidence theory.•The applicable coefficient of an index to a node is defined.•Experiments show the proposed method achieves superior performance.

论文关键词：Link prediction,Complex networks,Hybrid method,Evidence theory

论文评审过程：Received 2 April 2022, Revised 27 July 2022, Accepted 3 August 2022, Available online 6 August 2022, Version of Record 13 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118397