search

awslabs / dgl-ke

High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.
https://dglke.dgl.ai/doc/
Apache License 2.0
1.28k stars 196 forks source link

Interpretation of edge importance scores #249

Closed thomasthomasth closed 2 years ago

thomasthomasth commented 2 years ago

Hi,

Could you please speficy how to define edge important scores? This is an optinal parameter of the any of the models (TranE, Rotat, etc.)

I didn't find anything about this in the documentation.

An edge e1 with value 1.0 has a larger importance than another edge e2 with value 2.0? Or it should be interpreted the other way around?

classicsong commented 2 years ago

The higher the value, the more important the edge is.

thomasthomasth commented 2 years ago

@classicsong Thank you!