search

ixxi-dante / an2vec

Bringing node2vec and word2vec together for cool stuff
GNU General Public License v3.0
22 stars 6 forks source link

Train BlogCatalog without node features #37

Open wehlutyk opened 6 years ago

wehlutyk commented 6 years ago

i.e. with an identity matrix as features. Maybe extend that to training with BlogCatalog node features to which an identity matrix is concatenated, to make sure the model has enough information to separate the nodes based on features.

This tests if the bad adjacency reconstruction we're seeing in #31 comes from not being able to separate nodes based on their features.

wehlutyk commented 6 years ago

This exhausts the memory with the current implementation. We need to fix #24.