Representing spatial data with graph contrastive learning

HIGHLIGHTS

• who: Lanting Fang and collaborators from the School of Cyber Science and Engineering, Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China have published the Article: Representing Spatial Data with Graph Contrastive Learning, in the Journal: (JOURNAL)
• what: The authors propose a skeleton graph to preserve the primary structure of the geospatial graph to solve the positioning bias problem of remote sensing. The authors propose a heterogeneous graph attention network to aggregate information from both the structural neighborhood and semantic neighborhood separately. The authors focus on the representation of the nodes . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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