Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PCA visualisation: independent node2vec vs joint feature space #6

Open
deweihu96 opened this issue Jan 23, 2024 · 0 comments
Open

PCA visualisation: independent node2vec vs joint feature space #6

deweihu96 opened this issue Jan 23, 2024 · 0 comments

Comments

@deweihu96
Copy link

Hi ~

Your work is awesome and interesting! I'm just curious about the PCA visualization in Figure 1 of your paper. As I'm thinking using UMAP or tsne might looks better since the embeddings are different from the actual features. Did you also compare the PCA of embeddings trained individually?

Best,
Dewei

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant