HiWalk: Learning node embeddings from heterogeneous networks

作者：

Highlights：

• A method of learning embeddings for given type of nodes in heterogeneous networks.

• A hierarchical method, leveraging the other part of nodes as “background knowledge”.

• More effective, efficient and concentrated in heterogeneous network learning.

• It can be applied to many real-world analysis tasks.

摘要

•A method of learning embeddings for given type of nodes in heterogeneous networks.•A hierarchical method, leveraging the other part of nodes as “background knowledge”.•More effective, efficient and concentrated in heterogeneous network learning.•It can be applied to many real-world analysis tasks.

论文关键词：Network analysis,Representation learning,Behavioral analysis,Random walk,Heterogeneous network

论文评审过程：Received 4 February 2018, Revised 15 October 2018, Accepted 20 November 2018, Available online 26 November 2018, Version of Record 11 December 2018.

论文官网地址：https://doi.org/10.1016/j.is.2018.11.008