English

Sample weighting as an explanation for mode collapse in generative adversarial networks

Machine Learning 2020-10-06 v1 Machine Learning

Abstract

Generative adversarial networks were introduced with a logistic MiniMax cost formulation, which normally fails to train due to saturation, and a Non-Saturating reformulation. While addressing the saturation problem, NS-GAN also inverts the generator's sample weighting, implicitly shifting emphasis from higher-scoring to lower-scoring samples when updating parameters. We present both theory and empirical results suggesting that this makes NS-GAN prone to mode dropping. We design MM-nsat, which preserves MM-GAN sample weighting while avoiding saturation by rescaling the MM-GAN minibatch gradient such that its magnitude approximates NS-GAN's gradient magnitude. MM-nsat has qualitatively different training dynamics, and on MNIST and CIFAR-10 it is stronger in terms of mode coverage, stability and FID. While the empirical results for MM-nsat are promising and favorable also in comparison with the LS-GAN and Hinge-GAN formulations, our main contribution is to show how and why NS-GAN's sample weighting causes mode dropping and training collapse.

Keywords

Cite

@article{arxiv.2010.02035,
  title  = {Sample weighting as an explanation for mode collapse in generative adversarial networks},
  author = {Aksel Wilhelm Wold Eide and Eilif Solberg and Ingebjørg Kåsen},
  journal= {arXiv preprint arXiv:2010.02035},
  year   = {2020}
}

Comments

41 pages, 21 figures, preprint

R2 v1 2026-06-23T19:02:48.075Z