Rich heterogeneous information preserving network representation learning

作者：

Highlights：

• A novel and unified heterogeneous information network representation learning framework is proposed, which integrates node proximities and semantic information.

• A meta-path based random walk strategy and the autoencoders are employed to preserve semantic and structural information of heterogeneous information networks.

• The comprehensive evaluations validate the superiority of our model against the state-of-the-arts.

摘要

•A novel and unified heterogeneous information network representation learning framework is proposed, which integrates node proximities and semantic information.•A meta-path based random walk strategy and the autoencoders are employed to preserve semantic and structural information of heterogeneous information networks.•The comprehensive evaluations validate the superiority of our model against the state-of-the-arts.

论文关键词：Network representation learning,Heterogeneous information,Autoencoder

论文评审过程：Received 4 March 2019, Revised 18 May 2020, Accepted 21 July 2020, Available online 22 July 2020, Version of Record 26 July 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107564