Negative learning implementation in pytorch

Question

I have read a paper on Negative Learning: https://arxiv.org/abs/1908.07387. The idea is that you can train a network not only by telling what label of the sample is, but by telling what it surely is not. Let's call the latter a "negative" label.

An excerpt from the paper says (top formula is for usual "positive" label loss (PL), bottom - for "negative" label loss (NL):

I have a problem where "negative" labels collection is much easier than labeling each sample. So it is tempting to use it.

Is there some implementation of such a loss function in pytorch? Or should I write a custom loss layer code? If so, how should I do it?

Answer 1

One implementation is

( (loss+loss_neg) / (float((labels>=0).sum())+float((labels_neg[:,0]>=0).sum())) ).backward()

from NLNL-Negative-Learning-for-Noisy-Labels GitHub repo.