Comments (4)
@jsyoon0823 do you know why this happens? Your input would be appreciated
from gain.
Hello,
The default hyper-parameters should be optimized for each dataset.
GAN training needs a little more considering for optimizing hyper-parameters such as iterations, batch size, and hint rate.
Keep checking whether the discriminator and generator are well-balanced as well.
With some hyper-parameter optimizations, I can achieve RMSE 0.0513 which cannot be achieved by MSE loss only.
from gain.
@jsyoon0823 thank you for the suggestions. What would be a good choice of hyperparameters for the Spam dataset?
I am mostly struggling with getting decent performance without the supervised loss. For example, when I set alpha=0
, in the best case scenario I only get an RMSE of ~0.2 for the Spam dataset (far from the reported average RMSE of ~0.07). Do you have any suggestions on how to tune the hyperparameters for this particular case? Thanks a lot for your help
from gain.
Without supervised loss, you need to control the GAN training more seriously.
Supervised loss has some regularization effects; thus, it can stabilize the GAN training. However, without this supervised loss, GAN training is a little more unstable.
In this case, you need to do some early stopping (or best model saving) with the criteria of supervised loss. Even though you do not directly use the supervised loss for training the model, you can use it for early stopping. It will make you achieve the reported performance.
from gain.
Related Issues (20)
- How to decide Missingness Mechanism HOT 1
- Differences with the paper HOT 1
- Using GAIN in inductive mode HOT 1
- Changing only missing values? and scoring? HOT 1
- Why not both L_G and L_D relevant to V(D,G)? HOT 1
- Could you please provide Requirements.txt file HOT 1
- My dataset is 203454KB, I can't get the dataset after filling, because my dataset is too big? It gives some mistakes. HOT 1
- mixed (categorical and numerical) data HOT 3
- Model for the MNIST dataset HOT 1
- alpha HOT 1
- original data HOT 1
- Hyperparameters training HOT 3
- hyperparameters HOT 3
- RMSE is not stable HOT 1
- RMSE HOT 1
- Hint matrix HOT 1
- Why isn't the loss calculated only with b_i=0 values of the Hints. HOT 2
- No split training and testing sets? HOT 2
- Training Query HOT 1
- about minibatch 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 gain.