EmbeddGAN：一种使用嵌入网络和Gini距离相关的新型GAN框架
EmbeddGAN: A Novel GAN Framework Using an Embedding Network and Gini Distance Correlation
浏览论文内容
中文总结 AI 辅助
EmbeddGAN提出一种基于依赖目标的新型GAN框架，用嵌入网络和Gini距离相关替代判别器，通过极小极大策略训练，在MNIST、CIFAR-10和CelebA上实现竞争性能且训练稳定。
中文摘要 AI 辅助
生成对抗网络（GAN）在生成高质量合成数据方面展现了强大的性能。然而，它们受到缺乏关于收敛性和学习过程有效性的正式保证的限制。在实践中，这导致训练不稳定、模式崩溃以及对超参数的敏感性。为了解决这个问题，我们提出了EmbeddGAN，一种基于依赖目标的新型对抗训练框架。EmbeddGAN不依赖于将样本分类为真实或虚假的判别器，而是引入一个嵌入网络，学习一种表示，在该表示中，样本与其真实/虚假标签之间的统计依赖性被最大化，而生成器被训练为最小化这种依赖性。该目标使用Gini距离相关（gCor）来实现，当且仅当嵌入与真实/虚假标签统计独立时，gCor等于零。因此，最小化该目标鼓励真实样本和生成样本在学习的嵌入空间中变得统计上不可区分。嵌入网络将真实数据和生成数据投影到一个共享的低维空间中，在该空间中，分布差异可以通过成对距离直接测量。我们采用极小极大训练策略：嵌入网络最大化Gini距离相关（最大化依赖性），而生成器最小化它（最小化依赖性）。在MNIST、CIFAR-10和CelebA数据集上的实验表明，EmbeddGAN相对于已建立的基线实现了有竞争力的性能，同时在所评估的数据集上表现出显著稳定的训练动态。
英文摘要
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.
发表机构
- University of Mississippi（密西西比大学）
机构由 AI 辅助整理，请以论文原文为准。
