Take One Gram of Neural Features, Get Enhanced Group Robustness. (arXiv:2208.12625v1 [cs.LG])

Predictive performance of machine learning models trained with empirical risk
minimization (ERM) can degrade considerably under distribution shifts. The
presence of spurious correlations in training datasets leads ERM-trained models
to display high loss when evaluated on minority groups not presenting such
correlations. Extensive attempts have been made to develop methods improving
worst-group robustness. However, they require group information for each
training input or at least, a validation set with group labels to tune their
hyperparameters, which may be expensive to …

arxiv features lg robustness