邓晓衡

X. Deng, P. Jiang, D .Zhao, et al. Effective semi-supervised learning for structured data using Embedding GANs[J]. Pattern Recognition Letters, 2021, 151: 127-134.

发布时间：2024-03-13

点击次数：

发表刊物：Pattern Recognition Letters

摘要：The semi-supervised learning(SSL) was proposed to deal with the situation that only a few samples were labeled, so how to make the most use of the existing samples is crucial. In general, we apply data augmentation methods, like Generative Adversarial Networks(GAN), to increase the number of data when facing unstructured data. However, things get totally different with structured data, the continuity of neural networks limits their use in category variables. In this paper, we propose a semi-supervised Embedding GAN(EmGAN) to solve that problem. We add an embedding layer before the discriminator to better characterize category features and design a new loss function to further train our model. Moreover, the structures of the generator and discriminator are modified to match structured data. With the experiments of nonparametric statistical test, EmGAN shows its advantages in processing structured samples.

备注：http://faculty.csu.edu.cn/dengxiaoheng/zh_CN/lwcg/10445/content/49272.htm

是否译文：否

附件：