Imbalanced Classification via Explicit Gradient Learning From Augmented Data. (arXiv:2202.10550v2 [cs.LG] UPDATED)

Learning from imbalanced data is one of the most significant challenges in
real-world classification tasks. In such cases, neural networks performance is
substantially impaired due to preference towards the majority class. Existing
approaches attempt to eliminate the bias through data re-sampling or
re-weighting the loss in the learning process. Still, these methods tend to
overfit the minority samples and perform poorly when the structure of the
minority class is highly irregular. Here, we propose a novel deep meta-learning
technique to …

arxiv augmented data classification data gradient