.png){kind=icon}
返回
Deep self-supervised clustering with embedding adjacent graph features
.png){kind=icon}
OA
AI
DOI：10.1080/21642583.2022.2048321.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep clustering uses neural networks to learn the low-dimensional feature representations suitable for clustering tasks. Numerous studies have shown that learning embedded features and defining the clustering loss properly contribute to better performance. However, most of the existing studies focus on the deep local features and ignore the global spatial characteristics of the original data space. To address this issue, this paper proposes deep self-supervised clustering with embedding adjacent graph features (DSSC-EAGF). The significance of our efforts is three-fold: 1) To obtain the deep representation of the potential global spatial structure, a dedicated adjacent graph matrix is designed and used to train the autoencoder in the original data space; 2) In the deep encoding feature space, the KNN algorithm is used to obtain the virtual clusters for devising a self-supervised learning loss. Then, the reconstruction loss, clustering loss, and self-supervised loss are integrated, and a novel overall loss measurement is proposed for DSSC-EAGF. 3) An inverse-Y-shaped network model is designed to well learn the features of both the local and the global structures of the original data, which greatly improves the clustering performance. The experimental studies prove the superiority of the proposed DSSC-EAGF against a few state-of-the-art deep clustering methods.
Keyword:
Deep clustering
adjacent graph features
self-supervised learning
期刊
IF:
4.4
论文数:
486
被引数:
2.1K
机构
引用论文
Tunable terahertz dual-band band-stop filter based on surface magnetoplasmons in graphene sheet array基于石墨烯片阵列中表面磁等离极化激元的可调太赫兹双频带阻滤波器
PREAI
分享收藏Does deep learning help topic extraction? A kernel k-means clustering method with word embedding
OAAI
OAAI分享收藏Tailoring Optoelectronic Properties of ZnO Nanoparticles via Incorporation of Multiwalled Carbon Nanotube Contents on of ZnO/MWCNT Nanocomposites通过引入多壁碳纳米管含量来调节ZnO/MWCNT纳米复合材料的ZnO纳米颗粒的光电性能
PREAI
分享收藏A Review of Technical Impact of Electrical Vehicle Charging Stations on Distribution Grid电动汽车充电站对配电网的技术影响研究综述
PREAI
分享收藏Measurement Precision and Thermal and Absorption Properties of Nanostructures in Aqueous Solutions by Transient and Steady-State Thermal-Lens Spectrometry瞬态和稳态热透镜光谱法测量水溶液中纳米结构的测量精度及热和吸收特性.png)
PhyschemOAAI
PhyschemIF0
OAAI分享收藏
查看更多内容