Comments (10)
I decreased the learning rate to 1e-4 for both the discriminator and the generator, and trained for 100 epochs. The accuracy for G is about 51% and the accuracy for D is about 60%, which is still a little different from the paper. So I am wondering could anyone share the exact parameters to get the 80%+ accuracy? Thanks a lot.
from graphgan.
I met this problem too. The accuracy at the first iteration is about 76%, but after 20 iterations, the accuracy is about 50%. I don't know why. Is this because the data generated by the generator is similar to the true data?( I guess.)
If you know reason, would you please share it will me?
Thank you!
from graphgan.
Me too, both generator and discriminator are decreasing in accuracy. It seems that the link prediction result is a little different from the paper.
from graphgan.
I met this problem when training other GANs, my guess is that since the generator and discriminator both evoluted under training process, I can see the GAN successfully learned features from real data, when the accuracy starts to drop, it may means that generator can not dig more useful feature from real data, which means you need to adjust your model(for instance a new loss function) or add more data.
from graphgan.
Me too.
from graphgan.
Hi guys! I suggest decreasing the learning rate.
from graphgan.
我把lr_gen和lr_dis设成1e-5,batch_size设置成1024,在epoch 30的时候gen的accuracy达到最大0.884,比论文中的accuracy高一些
from graphgan.
I decreased the learning rate to 1e-4 for both the discriminator and the generator, and trained for 100 epochs. The accuracy for G is about 51% and the accuracy for D is about 60%, which is still a little different from the paper. So I am wondering could anyone share the exact parameters to get the 80%+ accuracy? Thanks a lot.
I set the learning rate to 1e-5 and I succeeded.It can be set to 1e-6 for greater accuracy, but it also requires more iterations than the default config.
from graphgan.
I think you can read the paper CFGAN
, it seems to explan the reason of that
from graphgan.
I decreased the learning rate to 1e-4 for both the discriminator and the generator, and trained for 100 epochs. The accuracy for G is about 51% and the accuracy for D is about 60%, which is still a little different from the paper. So I am wondering could anyone share the exact parameters to get the 80%+ accuracy? Thanks a lot.
I set the learning rate to 1e-5 and I succeeded.It can be set to 1e-6 for greater accuracy, but it also requires more iterations than the default config.
so how many iterations you succeeded when set the learning rate to 1e-5? by default?
from graphgan.
Related Issues (20)
- pretrained embeddings HOT 1
- could you share the code of Node classification?
- A serious BUG? HOT 1
- How can you get the test_neg.txt file? HOT 1
- Error of reading the pre_trained embedding?
- About Generative Probability HOT 2
- 关于emb初始化
- No module named src HOT 5
- Running too slow, can use gpu to speed up
- 请问节点分类的数据集是使用哪一个呢?可以共享吗? HOT 2
- FileNotFoundError: [Errno 2] No such file or directory: '../../results/link_prediction/CA-GrQc_gen_.emb' HOT 3
- rien
- I have two questions
- Evaluation of the link prediction for D and G
- I reimplement this paper and add other two experiments HOT 1
- FileNotFoundError: [Errno 2] No such file or directory: '../../cache/CA-GrQc.pkl' how to solve this problem? HOT 2
- 公式7->公式8的推导问题
- Generator and Discriminator embeddings
- Number of Nodes in the pre-training embedding file
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 graphgan.