A Structure-Enriched Neural Network for network embedding
作者：
Highlights：
• A structure-enriched framework for network embedding from a holistic perspective.
• Introducing the direction tuning parameters into multi-order transition matrices.
• Using the denoise autoencoder to do the dimension reduction of multi-order matrices.
• Employing the method with attention mechanism to combine multi-order information.
摘要
•A structure-enriched framework for network embedding from a holistic perspective.•Introducing the direction tuning parameters into multi-order transition matrices.•Using the denoise autoencoder to do the dimension reduction of multi-order matrices.•Employing the method with attention mechanism to combine multi-order information.
论文关键词：Network embedding,Direction adjustment,Attention mechanism
论文评审过程：Received 8 May 2018, Revised 23 August 2018, Accepted 18 September 2018, Available online 19 September 2018, Version of Record 2 October 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.09.040
