Comments (3)
Hi @robertanto, thanks for being patient. We've just put out the new PyKEEN v1.0 today, with a complete re-write of everything. There's much more documentation (though it still has a long way to go since there are so many features now)
You can check out the pykeen.pipeline
tutorial which will get you training your first model in a few lines of code, then you can start reading the pykeen.pipeline
reference to learn more, and lead yourself to all of the tricky configurations possible for each model, loss function, regularizer etc.
At this point, your feedback will be valued greatly, as we're moving towards doing a documentation sprint.
I'm not sure about Graph Neural Networks... @sharifza has implemented R-GCN for PyKEEN 1.0 so you can direct any specific questions about that to him. Since PyKEEN isn't really a framework for building new tools like PyTorch or PyTorch Geometric, there might be a misunderstanding. You can always use those tools to implement models then make them fit the interface for PyKEEN (in the mean time, PyTorch lightning was published which does something very similar to PyKEEN)
from pykeen.
Hi @robertanto, I think you have mistaken Knowledge Graph embedding models with Graph Conv Neural Networks. Although as @cthoyt mentioned, R-GCN is based on Graph Conv Neural Networks, I'm not sure if your question is directed specifically to that model. If my assumption is right, I would direct you to this and this paper.
from pykeen.
Thank you both @sharifza and @cthoyt !
Yes, for me the R-GCN model is a sufficient example.
from pykeen.
Related Issues (20)
- Question about the use of `create_inverse_triples` HOT 2
- Want to train a model without any evaluate or test dataset HOT 1
- Bug in wandb result tracker HOT 1
- Possible issue with model evaluation when using datasets with inverse triples HOT 1
- RGCN RuntimeError: trying to backward through graph a second time. (has parameters but no reset_parameters) HOT 2
- QuatE: GPU memory is not released per epoch HOT 3
- Training loop does not update relation representations when continuing training HOT 2
- from pykeen.pipeline import pipeline, pipeline issue HOT 3
- Evaluating metrics on many subsets with multiple models HOT 2
- Shape Mismatch upon initializing pretrained ComplEx embeddings HOT 2
- TransE - CUDA out of memory HOT 3
- Importing model_resolver HOT 2
- Getting Embeddings of the Entity and Relations HOT 13
- RGCN Hyper parameter optimization error HOT 1
- MatKG HOT 1
- HPO_Pipeline fails on AutoSF models HOT 1
- Unable to reproduce TransE experiment
- EarlyStopper: show progress bar
- Cosine Annealing with Warm Restart LR Scheduler recieving an unexpected kwarg `T_i`
- OOM Crash on MPS/Apple silicon HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pykeen.