Replies: 1 comment 2 replies
-
Note that this is for unsupervised training. I think it is easily possible to get to 80% when using supervised training of GraphSAGE. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I find the accuracy of some paper is more than 80% by using graphsage model on Cora dataset.However,the code of the link is just 75%.Why?How can I improve accuracy?
Beta Was this translation helpful? Give feedback.
All reactions