I have questions when reading example codes about the RGCN model.
In the entity classify task, the model use the AIFB data with different entity and edge types, the graph data should be heterogeneous. However, the graph in the model training process is a homograph rather than a heterograph. So my basic questions are:
- Why the training graph is a homograph with node and edge types rather than a heterograph?
- What are the differences between homograph with relations and heterograph in RGCN?
Thanks a lot!