# Does Adversarial Oversampling Help us?

arXiv: https://arxiv.org/abs/2108.10697 · HTML: https://mlsanity.com/paper/2108.10697/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 20 Aug 2021.

## Builds on (most cited first, 4 of 4)

- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Complement Objective Training](https://mlsanity.com/paper/1903.01182/) (2019)

## Built on by (most cited first, 3 of 3)

- [Multi-Fake Evolutionary Generative Adversarial Networks for Imbalance Hyperspectral Image Classification](https://mlsanity.com/paper/2111.04019/) (2021)
- [Latent Preserving Generative Adversarial Network for Imbalance classification](https://mlsanity.com/paper/2209.01555/) (2022)
- [Improving Self-supervised Learning for Out-of-distribution Task via Auxiliary Classifier](https://mlsanity.com/paper/2209.02881/) (2022)

## Abstract (arXiv)

Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer an end-to-end solution. To overcome this, we propose a three-player adversarial game-based end-to-end method, where a domain-constraints mixture of generators, a discriminator, and a multi-class classifier are used. Rather than adversarial minority oversampling, we propose an adversarial oversampling (AO) and a data-space oversampling (DO) approach. In AO, the generator updates by fooling both the classifier and discriminator, however, in DO, it updates by favoring the classifier and fooling the discriminator. While updating the classifier, it considers both the real and synthetically generated samples in AO. But, in DO, it favors the real samples and fools the subset class-specific generated samples. To mitigate the biases of a classifier towards the majority class, minority samples are over-sampled at a fractional rate. Such implementation is shown to provide more robust classification boundaries. The effectiveness of our proposed method has been validated with high-dimensional, highly imbalanced and large-scale multi-class tabular datasets. The results as measured by average class specific accuracy (ACSA) clearly indicate that the proposed method provides better classification accuracy (improvement in the range of 0.7% to 49.27%) as compared to the baseline classifier.