← Back to all news
arXiv Machine Learning By MaTais Caldwell, Yixin Chen, Xin Dang, Charles Walter

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

Read the original on arXiv Machine Learning →

EmbeddGAN introduces a new GAN framework that replaces the traditional discriminator with an embedding network trained to maximize statistical dependence between embeddings and real/fake labels using Gini distance correlation (gCor). The generator simultaneously minimizes this dependence, encouraging real and generated samples to become indistinguishable in the learned low‑dimensional embedding space. Experiments on MNIST, CIFAR‑10, and CelebA show competitive performance and notably more stable training dynamics compared to established baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 8

Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization

arXiv:2508. 01725v5 Announce Type: replace Abstract: Recent advances in continuous conditional generative modeling, including Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (CCDM), estimate high-dimensional data distributions conditioned on scalar regression labels such as angles, ages, or temperatures.

By Xin Ding, Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang
diffusionsafety
More like this →
arXiv Machine Learning
Oct 23

Revisiting GAN with Bayes-Optimal Discrimination

The paper reexamines GAN training by replacing the traditional cross‑entropy discriminator with an upper bound on the Bayes error rate, using the Bayes optimal learning threshold (BOLT) loss. It shows that, with balanced class priors, the resulting adversarial game is equivalent to minimizing total variation between data and generator distributions, and introduces BOLT‑GAN when the discriminator is constrained to be 1‑Lipschitz. Experiments on four image‑generation benchmarks demonstrate that BOLT‑GAN achieves better sample quality and coverage than WGAN‑GP, reducing FID scores on CIFAR‑10 and LSUN Bedroom‑64 within a 20‑epoch budget.

By Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero III
diffusionbenchmarkssafety
More like this →