低秩张量分解的多视角谱聚类算法

程士卿 1; 2; 郝问裕 1; 李晨 1; 张茁涵 1; 曹容玮 1

doi:10.7652/xjtuxb202003015

您当前的位置：

首页 >

文章列表页 >

低秩张量分解的多视角谱聚类算法

更新时间：2025-07-09

- 低秩张量分解的多视角谱聚类算法
- Multi-View Clustering by Low-Rank Tensor Decomposition
- 西安交通大学学报 2020年54卷第3期页码：119-125+133
- 作者机构：
  
  1. 西安交通大学软件学院,西安,710049
  2. 轨道交通工程信息化国家重点实验室(中铁一院),西安,710043
- 作者简介：
- 基金信息：
  
  : 2019-08-16。作者简介: 程士卿(1997—),女,硕士生;李晨(通信作者),女,讲师。基金项目: 轨道交通工程信息化国家重点实验室(中铁一院)资助项目(SKLK19-07);国家自然科学基金资助项目(61573273)
- DOI：10.7652/xjtuxb202003015
  中图分类号： TP391
- 网络首发：2020-03-10，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
程士卿 1, 2, 郝问裕 1, 等. 低秩张量分解的多视角谱聚类算法[J]. 西安交通大学学报, 2020,54(3):119-125+133.

Multi-View Clustering by Low-Rank Tensor Decomposition[J]. 2020, 54(3): 119-125+133.
程士卿 1, 2, 郝问裕 1, 等. 低秩张量分解的多视角谱聚类算法[J]. 西安交通大学学报, 2020,54(3):119-125+133. DOI： 10.7652/xjtuxb202003015.

Multi-View Clustering by Low-Rank Tensor Decomposition[J]. 2020, 54(3): 119-125+133. DOI： 10.7652/xjtuxb202003015.

摘要

针对传统多视角学习算法只关注从多视角中提取共享信息而忽略了各视角的特有信息和高阶关联的问题

提出了一种基于截断核范数的低秩张量分解的多视角谱聚类算法。计算各视角的样本相似度矩阵和转移概率矩阵

构建一个包含各视角马尔可夫转移概率矩阵的张量

从而保留各个视角的信息。采用基于张量奇异值分解的截断核范数约束目标张量的秩。通过最小化张量截断核范数

学习到一个既包含各个视角共享信息又具有高阶关联的张量。利用迭代最优化算法求解目标函数

将求得的目标张量输入谱聚类算法得到聚类结果。在4个不同类型数据集上进行实验并与传统聚类算法进行了对比

结果表明:所提算法在4个数据集上的标准互信息度量值比标准谱聚类算法的分别提高了7.9%、24.9%、29.5%、8.1%

比LT-MSC算法的分别提高了3.4%、18.1%、17.6%、6.6%。通过对非负平衡参数在0.000 1～100之间的测试发现

所提算法表现基本稳定

在非负平衡参数取0.1～1之间表现良好。与传统多视角聚类算法相比

所提算法可有效增强各视角之间的互补性和高阶关联

并且具有良好的准确性和鲁棒性。

Abstract

To solve the problem that the traditional multi-view learning methods cannot fully explore the consensus information among different views

a low-rank tensor decomposition multi-view spectral clustering algorithm based on truncated nuclear norm is proposed. The similarity matrix and transition probability matrix of each view are firstly obtained

then a tensor based on multi-view transition probability matrices is constructed. Tensor singular value decomposition based tensor truncated nuclear norm is imposed to preserve the low-rank property of the common tensor. Minimi-ing the tensor truncated kernel norm

a tensor containing both shared information and high-order correlations can be obtained properly via learning. The proposed method can be efficiently optimi-ed by the alternating direction method of multipliers. Experimental results on 4 datasets show that compared with standard spectral clustering

the value of normali-ed mutual information is enhanced by 7.9%

24.9%

29.5% and 8.1

关键词

Keywords

references

VON LUXBURG U. A tutorial on spectral clustering [J]. Statistics and Computing, 2007, 17(4): 395-416.

贾建华, 焦李成, 柳炳祥. 图像分割的谱聚类集成算法 [J]. 西安交通大学学报, 2010, 44(6): 93-98.

JIA Jianhua, JIAO Licheng, LIU Bingxiang. A spectral clustering ensemble algorithm for image segmentation [J]. Journal of Xi’an Jiaotong University, 2010, 44(6): 93-98.

NG A Y, JORDAN M I, WEISS Y. On spectral clustering: analysis and an algorithm [C]∥Proceedings of the 15th Annual Neural Information Processing Systems Conference. San Diego, CA, USA: NIPS, 2002: 849-856.

杨清宇, 孙凤伟, 张曌, 等. 利用测地线距离的改进谱聚类算法 [J]. 西安交通大学学报, 2012, 46(8): 1-7.

YANG Qingyu, SUN Fengwei, ZHANG Zhao, et al. An improved spectral clustering algorithm using geodesic distance [J]. Journal of Xi’an Jiaotong University, 2012, 46(8): 1-7.

KUMAR A, DAUMé H. A co-training approach for multi-view spectral clustering [C]∥International Conference on International Conference on Machine Learning. Piscataway, NJ, USA: IEEE, 2011: 393-400.

KUMAR A, RAI P, DAUMé H. Co-regularized multi-view spectral clustering [C]∥Proceedings of the 24th International Conference on Neural Information Processing Systems. Piscataway, NJ, USA: IEEE, 2011: 1413-1421.

SHI J B, MALIK J. Normalized cuts and image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.

ZHOU D, BURGES C J C. Spectral clustering and transductive learning with multiple views [C]∥Proceedings of the 24th international conference on Machine learning. New York, USA: ACM, 2007: 1159-1166.

杨金鸿, 邓廷权. 基于距离度量学习的半监督多视角谱聚类算法 [J]. 四川大学学报(工程科学版), 2016, 48(1): 146-151.

YANG Jinhong, DENG Tingquan. A semi-supervised multiview spectral clustering algorithm based on distance metric learning [J]. Journal of Sichuan University(Engineering Science Edition), 2016, 48(1): 146-151.

XIA R, PAN Y, DU L, et al. Robust multi-view spectral clustering via low-rank and sparse decomposition [C]∥Proceedings of the 28th AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI, 2014: 2149-2155.

ZHAI L, ZHU J H, ZHENG Q H, et al. Multi-view spectral clustering via partial sum minimisation of singular values [J]. Electronics Letters, 2019, 55(6): 314-316.

唐永强, 张文生. 基于自步学习的鲁棒多样性多视角聚类 [J]. 中国图象图形学报, 2019, 24(8): 1338-1348.

TANG Yongqiang, ZHANG Wensheng. Robust and diverse multi-view clustering based on self-paced learning [J]. Journal of Image and Graphics, 2019, 24(8): 1338-1348.

贺艳芳, 梁书田. 优化加权多视角K-means聚类算法 [J]. 计算机技术与发展, 2019, 29(3): 81-84.

HE Yanfang, LIANG Shutian. Optimizing weighted multi-view K-means clustering algorithm [J]. Computer Technology and Development, 2019, 29(3): 81-84.

ZONG L, ZHANG X, LIU X, et al. Weighted multi-view spectral clustering based on spectral perturbation [C]∥Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI, 2018: 4621-4629.

ZHANG C, FU H, LIU S, et al. Low-rank tensor constrained multiview subspace clustering [C]∥Proceedings of the 2015 IEEE International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2015: 1582-1590.

XUE S, QIU W, LIU F, et al. Low-rank tensor completion by truncated nuclear norm regularization [C]∥Proceedings of the International Conference on Pattern Recognition(ICPR). Piscataway, NJ, USA: IEEE, 2018: 2600-2605.

XIE Y, TAO D C, ZHANG W S, et al. On unifying multi-view self-representations for clustering by tensor multi-rank minimization [J]. International Journal of Computer Vision, 2018, 126(11): 1157-1179.

LIU G C, LIN Z C, YAN S C, et al. Robust recovery of subspace structures by low-rank representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 171-184.

Digital Technology Group. ORL dataset [DS/OL]. [2019-08-01]. https: ∥www.cl.cam.ac.uk/research /dtg/attarchive/facedatabase.html.

LAZEBNIK S, SCHMID C, PONCE J. A sparse texture representation using local affine regions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1265-1278.

DUA D, GRAFF C. UCI machine learning repository [DS/OL]. [2019-08-01]. http: ∥archive.ics.uci. edu/ml/index.php.

CLéMENT G. Movies dataset [DS/OL]. [2019-08-01]. http: ∥membres-lig.imag.fr/grimal/data.html.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

扇贝仿生密封腔室内超临界二氧化碳泄漏流湍动能耗散机理研究

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究

张角凹坑气膜孔对双层壁气膜冷却特性的影响

融合物理信息与深度算子网络的变压器绕组热-流场快速计算方法

多工况下离心压气机叶轮-机匣一体联合设计优化