Exploring Implicit and Explicit Geometrical Structure of Data for Deep Embedded Clustering
文献类型：期刊论文
| 作者 | Zhu, Xiaofei2; Do, Khoi Duy3; Guo, Jiafeng4; Xu, Jun1; Dietze, Stefan5 |
| 刊名 | NEURAL PROCESSING LETTERS
 |
| 出版日期 | 2020-10-19 |
| 页码 | 16 |
| 关键词 | Deep neural networks Stacked autoencoder Manifold constraint Clustering |
| ISSN号 | 1370-4621 |
| DOI | 10.1007/s11063-020-10375-9 |
| 英文摘要 | Clustering is an essential data analysis technique and has been studied extensively over the last decades. Previous studies have shown that data representation and data structure information are two critical factors for improving clustering performance, and it forms two important lines of research. The first line of research attempts to learn representative features, especially utilizing the deep neural networks, for handling clustering problems. The second concerns exploiting the geometric structure information within data for clustering. Although both of them have achieved promising performance in lots of clustering tasks, few efforts have been dedicated to combine them in a unified deep clustering framework, which is the research gap we aim to bridge in this work. In this paper, we propose a novel approach, Manifold regularized Deep Embedded Clustering (MDEC), to deal with the aforementioned challenge. It simultaneously models data generating distribution, cluster assignment consistency, as well as geometric structure of data in a unified framework. The proposed method can be optimized by performing mini-batch stochastic gradient descent and back-propagation. We evaluate MDEC on three real-world datasets (USPS, REUTERS-10K, and MNIST), where experimental results demonstrate that our model outperforms baseline models and obtains the state-of-the-art performance. |
| 资助项目 | National Natural Science Foundation of China[61722211] ; Federal Ministry of Education and Research[01LE1806A] ; Natural Science Foundation of Chongqing[cstc2017jcyjBX0059] ; Beijing Academy of Artificial Intelligence[BAAI2019ZD0306] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000579720300001 |
| 出版者 | SPRINGER |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/15747]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Zhu, Xiaofei |
| 作者单位 | 1.Renmin Univ China, Sch Informat, Beijing 100872, Peoples R China 2.Chongqing Univ Technol, Coll Comp Sci & Engn, Chongqing 400054, Peoples R China 3.Leibniz Univ Hannover, Res Ctr L3S, D-30167 Hannover, Germany 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 5.Leibniz Inst Social Sci, Knowledge Technol Social Sci, D-50667 Cologne, Germany |
| 推荐引用方式 GB/T 7714 | Zhu, Xiaofei,Do, Khoi Duy,Guo, Jiafeng,et al. Exploring Implicit and Explicit Geometrical Structure of Data for Deep Embedded Clustering[J]. NEURAL PROCESSING LETTERS,2020:16. |
| APA | Zhu, Xiaofei,Do, Khoi Duy,Guo, Jiafeng,Xu, Jun,&Dietze, Stefan.(2020).Exploring Implicit and Explicit Geometrical Structure of Data for Deep Embedded Clustering.NEURAL PROCESSING LETTERS,16. |
| MLA | Zhu, Xiaofei,et al."Exploring Implicit and Explicit Geometrical Structure of Data for Deep Embedded Clustering".NEURAL PROCESSING LETTERS (2020):16. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
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。