LibMTL.weighting.RLW

class RLW[source]

Bases: LibMTL.weighting.abstract_weighting.AbsWeighting

Random Loss Weighting (RLW).

This method is proposed in Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning (TMLR 2022) and implemented by us.

backward(self, losses, **kwargs)[source]
Parameters

  • losses (list) – A list of losses of each task.

  • kwargs (dict) – A dictionary of hyperparameters of weighting methods.