Closed droully closed 3 years ago
When using SDNE, for a graph with n nodes, the resulting embedding is always of size n, independently of the dimension size. Maybe I'm doing something wrong? the command I'm using is:
python -m openne --model sdne --local-dataset --edgefile karate.edgelist --root-dir karate\
and the resulting embedding file is attached.
SDNE_embeddings.txt
Notice that the embedding is 34x34 but the default option is [1000, 128] so it should be 34x128.
Hi @droully, thanks for your question! This is a bug and we have fixed it in the latest commit.
When using SDNE, for a graph with n nodes, the resulting embedding is always of size n, independently of the dimension size. Maybe I'm doing something wrong? the command I'm using is:
python -m openne --model sdne --local-dataset --edgefile karate.edgelist --root-dir karate\
and the resulting embedding file is attached.
SDNE_embeddings.txt
Notice that the embedding is 34x34 but the default option is [1000, 128] so it should be 34x128.