Comments (2)
Hi,
There is label leakage in its training:
The negative sampling should only neglect the samples in the train set, not in the valid set or the test set. In other words, they shouldn't use valid_triples_dict (all triples in train, dev, and test) in this line, but should only use training data.
This is also true to: https://github.com/deepakn97/relationPrediction/blob/785721b758e9c87144b5d271dd5daaa46bb1e6ea/create_batch.py#L113
from kg-reeval.
We forgot to include the changes in the KBAT code in the Github version. Now, we have updated it. Please have a look.
from kg-reeval.
Related Issues (13)
- Unable to train ConvE on Fb15k-237 HOT 1
- confused about figure3 in paper HOT 1
- KBAT's hyper-parameter for each dataset HOT 1
- KBAT run error HOT 1
- KBAT:when i run your code , Iteration_loss show "nan". do you know what problem with it? HOT 1
- RotatE: local variable 'positive_arg' referenced before assignment HOT 2
- Unable to train ConvE on Fb15k-237 HOT 1
- can not find the file
- About KBGAT and RGHAT
- hi, want to know what's KGAT 's leakage problem HOT 4
- Why the problem of KBAT data leakage is not reflected in your code HOT 3
- Question about RotatE new evaluation. 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 kg-reeval.