pu-learning

pu-learning copied to clipboard

Hi, I'm doing some research using nnPU with binary classification. During my experiments, there is a problem that train loss & validation loss are decreasing just like the way loss...

Parkjunghoons2

In 'loss.py' , line 37-38 ``` if negative_risk < -self.beta and self.nnPU: return -self.gamma * negative_risk ``` Is this correct? I think the following is correct. ``` if negative_risk <...

takehiro-yamane

Cleanup loss function

1

Richienb