TensorFlow Implementation of ChoiceNet on regression tasks.
Paper: arxiv
Error type: [Permutation]
name | Result |
---|---|
Outlier Rate: 25.0% | ![]() |
Outlier Rate: 45.0% | ![]() |
Outlier Rate: 47.5% | ![]() |
Error type: [Random Shuffle]
name | Result |
---|---|
Outlier Rate: 50.0% | ![]() |
Outlier Rate: 90.0% | ![]() |
Outlier Rate: 95.0% | ![]() |
Error type: [Label Bias]
name | Result |
---|---|
Outlier Rate: 25.0% | ![]() |
Outlier Rate: 45.0% | ![]() |
Outlier Rate: 47.5% | ![]() |
Reference Function: [cosexp]
name | Training Data | Multi-Layer Perceptron | Mixture Density Network | ChoiceNet |
---|---|---|---|---|
oRate: 0.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 10.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 30.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 50.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 60.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 70.0% | ![]() | ![]() | ![]() | ![]() |
Reference Function: [linear]
name | Training Data | Multi-Layer Perceptron | Mixture Density Network | ChoiceNet |
---|---|---|---|---|
oRate: 0.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 10.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 30.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 50.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 60.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 70.0% | ![]() | ![]() | ![]() | ![]() |
Reference Function: [step]
name | Training Data | Multi-Layer Perceptron | Mixture Density Network | ChoiceNet |
---|---|---|---|---|
oRate: 0.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 10.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 30.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 50.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 60.0% | ![]() | ![]() | ![]() | ![]() |
oRate: 70.0% | ![]() | ![]() | ![]() | ![]() |
- run code/main_reg_run.ipynb
- Properly modify followings based on the working environment:
nWorker = 16
maxGPU = 8
- (I was using 16 CPUs / 8 TESLA P40s / 96GB RAM.)
- Python3
- TF 1.4>=
This work was done in Kakao Brain.