Comments (1)
Hi,
Just want to clarify that we didn't do intimacy matrix calculation in step 1... In the step 1, we calculate the WL code of nodes.
If you plan to use different sampling algorithm, you just need to re-implement step 2 in the pre-processing script with your own sampling approach. You can rewrite "MethodGraphBatching.py" with your own sampling class instead. Just FYI.
Best,
Jiawei
from graph-bert.
Related Issues (20)
- Graph representation of custom dataset and ASTs HOT 2
- How could I get the data of citeseer and pubmed?
- Are there some tricks in the stage of fine-tuning?
- [Question] Position-Embed function Eqn. 3 HOT 2
- Code doesn't match paper HOT 1
- transformer edition
- transformers edition HOT 1
- ModuleNotFoundError: No module named 'transformers.modeling_bert' HOT 1
- Too many errors in script 4 evalution HOT 1
- Custom dataset: float feature values
- Running script_2_pre_train for Node Attribute Reconstruction and Graph Bert Network Structure Recovery HOT 1
- Activation function implementation
- Why it is running on CPU? HOT 2
- About the size of the input graph HOT 3
- > you can change the code to use mini-batch instead
- About mini-batch size HOT 1
- nfeature, ngraph HOT 1
- [question] Weight Loading HOT 1
- Some questions about intimacy matrix 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 graph-bert.