Improving network representation learning via dynamic random walk, self-attention and vertex attributes-driven laplacian space optimization

HIGHLIGHTS

• who: Shengxiang Hu et al. from the School of Computer Engineering and Science, Shanghai University, Shanghai, China have published the article: Improving Network Representation Learning via Dynamic Random Walk, Self-Attention and Vertex Attributes-Driven Laplacian Space Optimization, in the Journal: Entropy 2022, 24, 1213. of 25/07/2022
• what: To address the aforementioned issues, the authors propose a general NRL approach called dynamic structure and vertex attributes fusion network embedding (dSAFNE). Based on a newly defined asymmetric second-order vertex approximity, the authors design an h-hop weighted dynamic random walk strategy, which incorporates . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.