Skip to content
Discussion options

You must be logged in to vote

Sorry for the confusion.

  • edge_index denotes the edges that are used for message passing inside a GNN
  • edge_label_index denote the pairs of nodes that are used for supervision/loss computation. For example, we try to predict new pairs of links in edge_label_index after propagating information and learning node embeddings based on edge_index. In addition, as you correctly pointed out, edge_label_index contains both positive and negative pairs of examples.

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@Jeriousman
Comment options

Answer selected by Jeriousman
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants