Toward Understanding Generative Data Augmentation

Understand

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot learning, and adversarially robust learning.

• However, little work has theoretically investigated the effect of generative data augmentation.
• To fill this gap, we establish a general stability bound in this not independently and identically distributed (non-i.i.d.) setting, where the learned distribution is dependent on the original train set and generally not the same as the true distribution.
• Our theoretical result includes the divergence between the learned distribution and the true distribution.