-
-
Notifications
You must be signed in to change notification settings - Fork 179
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
⬇️🎖️ Low rank embeddings #680
Conversation
also improve docstring trigger ci
trigger ci
@@ -594,197 +653,6 @@ def _handle( | |||
return value | |||
|
|||
|
|||
class RGCNRepresentations(RepresentationModule): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I had to move this one to avoid cyclic imports
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🚨🚨 IT'S THE DOCUMENTATION POLICE, OPEN UP 🚨🚨
besides the notes on improving the docs, I think this all looks solid. the moves for the circular imports make sense though they make me wonder if we should adopt pytorch-like way of just importing everything in pykeen.nn
@PyKEEN-bot test |
Trigger CI
@PyKEEN-bot test |
This PR adds a representation module, which factorizes the
Embedding
matrix into a matrix of basis representations, and trainable linear weights.It is an alternative way to reduce the number of trainable parameters, while keeping the embedding dimension.
pykeen/src/pykeen/nn/message_passing.py
Lines 141 to 150 in c8f6af6
so there may be some potential to reduce duplication. -> 78d9b62