Nonnegative matrix factorization for link prediction in directed complex networks using PageRank and asymmetric link clustering information

作者：

Highlights：

• Introduce a model to fuse local and global information in directed network.

• The model can capture topological structures and robust to sparser networks.

• Present an effective update rule to learn model parameters.

• Experimental results show that our method is outperforms other indices.

摘要

•Introduce a model to fuse local and global information in directed network.•The model can capture topological structures and robust to sparser networks.•Present an effective update rule to learn model parameters.•Experimental results show that our method is outperforms other indices.

论文关键词：Link prediction,Nonnegative matrix factorization,PageRank,Asymmetric link clustering

论文评审过程：Received 9 February 2019, Revised 31 December 2019, Accepted 5 February 2020, Available online 6 February 2020, Version of Record 15 February 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113290