MBRep: Motif-based representation learning in heterogeneous networks

作者：

Highlights：

• Considering networks’ heterogeneity in embedding methods is effective.

• Triangle motifs preserve network heterogeneity and link directionality.

• Atomic-level motif embedding overcomes manual intervention.

• Higher-order heterogeneous connectivity patterns cope cold-start well.

摘要

•Considering networks’ heterogeneity in embedding methods is effective.•Triangle motifs preserve network heterogeneity and link directionality.•Atomic-level motif embedding overcomes manual intervention.•Higher-order heterogeneous connectivity patterns cope cold-start well.

论文关键词：Motif,Heterogeneous network,Representation learning,Cold-start

论文评审过程：Received 5 December 2020, Revised 2 August 2021, Accepted 2 October 2021, Available online 9 October 2021, Version of Record 10 November 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116031