发表状态 | 已发表Published |
题名 | Deep generative clustering methods based on disentangled representations and augmented data |
作者 | |
发表日期 | 2024-10-01 |
发表期刊 | International Journal of Machine Learning and Cybernetics
![]() |
ISSN/eISSN | 1868-8071 |
卷号 | 15期号:10页码:4575-4588 |
摘要 | This paper presents a novel clustering approach that utilizes variational autoencoders (VAEs) with disentangled representations, enhancing the efficiency and effectiveness of clustering. Traditional VAE-based clustering models often conflate generative and clustering information, leading to suboptimal clustering performance. To overcome this, our model distinctly separates latent representations into two modules: one for clustering and another for generation. This separation significantly improves clustering performance. Additionally, we employ augmented data to maximize mutual information between cluster assignment variables and the optimized latent variables. This strategy not only enhances clustering effectiveness but also allows the construction of latent variables that synergistically combine clustering information from original data with generative information from augmented data. Through extensive experiments, our model demonstrates superior clustering performance without the need for pre-training, outperforming existing deep generative clustering models. Moreover, it achieves state-of-the-art clustering accuracy on certain datasets, surpassing models that require pre-training. |
关键词 | Augmented data Clustering Disentangling module Mutual information Variational autoencoder (VAE) |
DOI | 10.1007/s13042-024-02173-9 |
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:001209381900001 |
Scopus入藏号 | 2-s2.0-85191749136 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/11970 |
专题 | 理工科技学院 |
通讯作者 | Fan, Wentao |
作者单位 | 1.Department of Computer Science and Technology, Huaqiao University, Xiamen, China 2.Guangdong Provincial Key Laboratory IRADS and Department of Computer Science, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai, China |
通讯作者单位 | 北师香港浸会大学 |
推荐引用方式 GB/T 7714 | Xu, Kunxiong,Fan, Wentao,Liu, Xin. Deep generative clustering methods based on disentangled representations and augmented data[J]. International Journal of Machine Learning and Cybernetics, 2024, 15(10): 4575-4588. |
APA | Xu, Kunxiong, Fan, Wentao, & Liu, Xin. (2024). Deep generative clustering methods based on disentangled representations and augmented data. International Journal of Machine Learning and Cybernetics, 15(10), 4575-4588. |
MLA | Xu, Kunxiong,et al."Deep generative clustering methods based on disentangled representations and augmented data". International Journal of Machine Learning and Cybernetics 15.10(2024): 4575-4588. |
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