Loss - only supervised?

cynricfu / MAGNN

Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

398 stars 69 forks source link

Loss - only supervised? #27

Closed sindhura97 closed 2 years ago

sindhura97 commented 3 years ago

In run_DBLP.py, I see that the model is only trained with supervised loss. Can you please confirm this as the paper also mentions an unsupervised loss?

cynricfu commented 3 years ago

Yes, for the DBLP dataset, MAGNN and other GNN baselines in my paper are trained only using the (semi-)supervised loss.