Unbalanced data in multi label problem

hi, I have a multi-label problem, and they are very rare classes, and on the other hand, some very common classes.
I have a custom loss
I need o use all my data
how can I balance this with my loss?

There are some sample weighting techniques for such data.
See: https://arxiv.org/abs/1803.09050

This is in fact something I personally implemented a few days ago. Maybe my implementation can help you: https://github.com/TinfoilHat0/Learning-to-Reweight-Examples-for-Robust-Deep-Learning-with-PyTorch-Higher

tnx, but i dont see there reference to the multi label problem

Hi what do you mean? in the experiments, they have an example on mnist where frequency of samples is heavily skewed towards digit 9. isnt that like your scenario?

oh i see. yeah in that case each sample is associated with only a single label, different than your scenario.