Structural Hierarchy-Enhanced Network Representation Learning
Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding spac...
Spremljeno u:
| Glavni autori: | , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
MDPI AG
2020-10-01
|
| Serija: | Applied Sciences |
| Teme: | |
| Online pristup: | https://www.mdpi.com/2076-3417/10/20/7214 |
| Oznake: |
Bez oznaka, Budi prvi tko označuje ovaj zapis!
|