Comments (8)
This is also easly solved by only computing a penalty for the parameters that were used in the batch, see https://github.com/facebookresearch/kbc/blob/master/kbc/regularizers.py
from kge.
Hmm, is the link you send actually correct? It should also matter how often the parameter is used in a batch.
from kge.
I am unassigning this from me (and, in fact, afaik Daniel was on this).
from kge.
factors is the batch of entities or relations, so if an entity/relation occurs multiple times will amount to it being weighted according to its frequency.
from kge.
Sounds good. Enabling this way of weighted regularization could be a separate regularizer (e.g., "sparse_l2"). Note that here one may need to proceed differently to stay independent of the batch size (see #35): the penalty term (in its implementation) needs to be scaled such that it its expectation is independent of the batch size.
from kge.
Yes, in fact this is what they do in their implementation, they divide the penalty term by batch size.
from kge.
Yep, this sounds good.
from kge.
I am closing this, discussion of this feature is in #41.
from kge.
Related Issues (20)
- Support more metrics?
- How to apply HittER
- Number of negative samples during evaluation HOT 3
- web.informatik.uni-mannheim.de not accesible HOT 2
- ValueError thrown by `$ kge start examples/toy-complex-train.yaml` HOT 3
- Using buffer for writing to a file during preprocessing
- ConvE and reciprocal_relations_model HOT 2
- Getting output of libKGE
- Relation Prediction HOT 5
- Filtered _ro prediction HOT 1
- Frequency based sampling broken
- Error on tensor scoring HOT 1
- Adding user keys to config HOT 2
- Trial XXXXX failed: TypeError("step() missing 1 required positional argument: 'closure'") HOT 2
- ERROR: file:///content does not appear to be a Python project: neither 'setup.py' nor 'pyproject.toml' found. HOT 3
- generate embeddings HOT 1
- Trained embeddings are missing for Codex-{S/M/L} HOT 1
- dataset issues HOT 3
- Getting model predictions in parallel HOT 1
- About debug the program 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 kge.