DiGCL icon indicating copy to clipboard operation
DiGCL copied to clipboard

intra loss

Open dhsiuu opened this issue 4 months ago • 0 comments

You mentioned in the article that "we do not treat intra-view nodes as negative samples since the GNN-based encoder is already able to learn intra-graph structure well; we want to focus on inter-graph contrastive information." However, you still used intra loss in the loss function code.

dhsiuu avatar Oct 23 '24 08:10 dhsiuu