Metraipolis › archive › dc_4bb49a04eaf0

EmbeddGAN: A Novel GAN Framework Using an Embedding Network and Gini Distance Correlation — arXiv:2609.22508

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22508
License (as archived)
CC0-1.0
Archived
2026-10-09T07:06:36.560Z
SHA-256 of the archived text
a3cc1ee5989f20408bd4e44a120fd5ec022520c86b9f99bba48ec9f0bbb2e981
Stable URL of this page
https://metraipolis.com/documento/dc_4bb49a04eaf0

How to cite

EmbeddGAN: A Novel GAN Framework Using an Embedding Network and Gini Distance Correlation — arXiv:2609.22508 — arXiv (en), https://arxiv.org/abs/2609.22508 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bb49a04eaf0 (Metraipolis archive dc_4bb49a04eaf0, sha256 a3cc1ee5989f20408bd4e44a120fd5ec022520c86b9f99bba48ec9f0bbb2e981)
BibTeX
@misc{dc4bb49a04eaf0,
  title = {EmbeddGAN: A Novel GAN Framework Using an Embedding Network and Gini Distance Correlation — arXiv:2609.22508},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22508},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bb49a04eaf0; sha256 a3cc1ee5989f20408bd4e44a120fd5ec022520c86b9f99bba48ec9f0bbb2e981},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22508. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative Adversarial Networks (GANs) have demonstrated strong performance in generating high-quality synthetic data. However, they are limited by no formal guarantees regarding convergence and the effectiveness of the learning process. In practice, this leads to training instability, mode collapse, and sensitivity to hyperparameters. To address this, we propose EmbeddGAN, a novel adversarial training framework based on a dependence-based objective. Instead of relying on a discriminator that classifies samples as real or fake, EmbeddGAN introduces an embedding network that learns a representation in which statistical dependence between samples and their real/fake labels is maximized, while the generator is trained to minimize this dependence. This objective is implemented using the Gini distance correlation (gCor), which equals zero if and only if the embeddings are statistically independent of the real/fake label. Minimizing this objective therefore encourages real and generated samples to become statistically indistinguishable in the learned embedding space. The embedding network projects both real and generated data into a shared low-dimensional space, where distributional discrepancies can be measured directly through pairwise distances. We adopt a minimax training strategy: the embedding network maximizes the Gini distance correlation (maximizing dependence), while the generator minimizes it (minimizing dependence). Experiments on the MNIST, CIFAR-10, and CelebA datasets demonstrate that EmbeddGAN achieves competitive performance relative to established baselines while exhibiting notably stable training dynamics on the evaluated datasets.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.22508 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:58:09.198Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).