Is it possible to check how DGL is pre-processing a dataset? For instance I want to check the kind of normalization DGL applies on Cora. Thank you in advance
You can read the source code at dgl/citation_graph.py at master · dmlc/dgl · GitHub.
Basically our preprocessing follows the original GCN paper
1 Like
I was looking exactly for that! thank you Allen
This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.