发表状态 | 已发表Published |
题名 | Unsupervised meta-learning via spherical latent representations and dual VAE-GAN |
作者 | |
发表日期 | 2023-10-01 |
发表期刊 | Applied Intelligence
![]() |
ISSN/eISSN | 0924-669X |
卷号 | 53期号:19页码:22775-22788 |
摘要 | Unsupervised learning and meta-learning share a common goal of enhancing learning efficiency compared to starting from scratch. However, meta-learning methods are predominantly employed in supervised settings, where acquiring labels for meta-training is costly and new tasks are limited to a predefined distribution of training tasks. In this paper, we introduce a novel unsupervised meta-learning framework that leverages spherical latent representations defined on a unit hypersphere. Unlike the state-of-the-art unsupervised meta-learning approach that assumes a Gaussian mixture prior over latent representations, we utilize a von Mises-Fisher mixture model for constructing the latent space. This alternative formulation leads to a more stable optimization process and improved performance. To enhance the generative capability of our model, we unify the variational autoencoder (VAE) and the generative adversarial network (GAN) within our unsupervised meta-learning framework. Moreover, we propose a dual VAE-GAN framework to impose a reconstruction constraint on both the latent representations and their corresponding transformed versions, thereby yielding more representative and discriminative representations. The efficacy of our proposed unsupervised meta-learning framework is demonstrated through extensive comparisons with existing methods on diverse benchmark datasets. |
关键词 | GAN Meta-learning Unsupervised learning VAE Von Mises-Fisher |
DOI | 10.1007/s10489-023-04760-9 |
URL | 查看来源 |
收录类别 | SCIE |
语种 | 英语English |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:001021395900002 |
Scopus入藏号 | 2-s2.0-85163776642 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/10896 |
专题 | 理工科技学院 |
通讯作者 | Fan, Wentao |
作者单位 | 1.Department of Computer Science,Beijing Normal University-Hong Kong Baptist University United International College (BNU-HKBU UIC),Zhuhai,Guangdong,China 2.Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science,BNU-HKBU United International College,Zhuhai,China 3.Department of Computer Science and Technology,Huaqiao University,Xiamen,China |
第一作者单位 | 北师香港浸会大学 |
通讯作者单位 | 北师香港浸会大学 |
推荐引用方式 GB/T 7714 | Fan, Wentao,Huang, Hanyuan,Liang, Chenet al. Unsupervised meta-learning via spherical latent representations and dual VAE-GAN[J]. Applied Intelligence, 2023, 53(19): 22775-22788. |
APA | Fan, Wentao, Huang, Hanyuan, Liang, Chen, Liu, Xin, & Peng, Shu Juan. (2023). Unsupervised meta-learning via spherical latent representations and dual VAE-GAN. Applied Intelligence, 53(19), 22775-22788. |
MLA | Fan, Wentao,et al."Unsupervised meta-learning via spherical latent representations and dual VAE-GAN". Applied Intelligence 53.19(2023): 22775-22788. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论