A structure-characteristic-aware network embedding model via differential evolution

作者：

Highlights：

• Provide a novel approach for disassortative network embedding.

• Multi-view extraction mixer captures and aggregates the 3 M structures into NMF.

• Adaptive aggregator adjusts the 3 M structures adaptively by DE.

• The proposed model achieves significant improvement over other related method.

摘要

•Provide a novel approach for disassortative network embedding.•Multi-view extraction mixer captures and aggregates the 3 M structures into NMF.•Adaptive aggregator adjusts the 3 M structures adaptively by DE.•The proposed model achieves significant improvement over other related method.

论文关键词：Network embedding,Non-negative matrix factorization,Network structure,Differential evolution

论文评审过程：Received 9 June 2021, Revised 24 April 2022, Accepted 15 May 2022, Available online 19 May 2022, Version of Record 24 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117611