Mitigating Mode Collapse using Multiple GANs Training System 


Vol. 13,  No. 10, pp. 497-504, Oct.  2024
https://doi.org/10.3745/TKIPS.2024.13.10.497


PDF
  Abstract

Generative Adversarial Networks (GANs) are typically described as a two-player game between a generator and a discriminator, where the generator aims to produce realistic data, and the discriminator tries to distinguish between real and generated data. However, this setup often leads to mode collapse, where the generator produces limited variations in the data, failing to capture the full range of the target data distribution. This paper proposes a new training system to mitigate the mode collapse problem. Specifically, it extends the traditional two-player game of GANs into a multi-player game and introduces a peer-evaluation method to effectively train multiple GANs. In the peer-evaluation process, the generated samples from each GANs are evaluated by the other players. This provides external feedback, serving as an additional standard that helps GANs recognize mode failure. This cooperative yet competitive training method encourages the generators to explore and capture a broader range of the data distribution, mitigating mode collapse problem. This paper explains the detailed algorithm for peer-evaluation based multi-GANs training and validates the performance through experiments.

  Statistics


  Cite this article

[IEEE Style]

J. Y. Shim, J. S. B. Choe, J. Kim, "Mitigating Mode Collapse using Multiple GANs Training System," The Transactions of the Korea Information Processing Society, vol. 13, no. 10, pp. 497-504, 2024. DOI: https://doi.org/10.3745/TKIPS.2024.13.10.497.

[ACM Style]

Joo Yong Shim, Jean Seong Bjorn Choe, and Jong-Kook Kim. 2024. Mitigating Mode Collapse using Multiple GANs Training System. The Transactions of the Korea Information Processing Society, 13, 10, (2024), 497-504. DOI: https://doi.org/10.3745/TKIPS.2024.13.10.497.