一种基于T-分布随机近邻嵌入的聚类集成方法

徐森; 花小朋; 徐静; 徐秀芳; 皋军; 安晶

doi:10.11999/JEIT170937

一种基于T-分布随机近邻嵌入的聚类集成方法

doi: 10.11999/JEIT170937

基金项目:

国家自然科学基金(61105057, 61375001)，江苏省自然科学基金(BK20151299)，江苏省产学研前瞻性联合研究项目(BY2016065-01)

计量
- 文章访问数: 701
- HTML全文浏览量: 118
- PDF下载量: 120
- 被引次数: 0
出版历程
- 收稿日期: 2017-10-10
- 修回日期: 2018-03-16
- 刊出日期: 2018-06-19

Cluster Ensemble Approach Based on T-distributed Stochastic Neighbor Embedding

Funds:

The National Natural Science Foundation of China (61105057, 61375001), The Natural Science Foundation of Jiangsu Province (BK20151299), The Industry-Education-Research Prospective Project of Jiangsu Province (BY2016065-01)

摘要

摘要: 该文将T-分布随机近邻嵌入(TSNE)引入到聚类集成问题中，提出一种基于TSNE的聚类集成方法。首先通过TSNE最小化超图邻接矩阵的行对应的高维数据点与低维映射点分布之间的KL散度，使得高维空间结构在低维空间得以保持，然后在低维空间运行层次聚类算法获得最终的聚类结果。在基准数据集上的实验结果表明： TSNE能够提高层次聚类算法的聚类质量，该文方法获得了优于主流聚类集成方法的结果。
- 机器学习 /
- 聚类分析 /
- 聚类集成 /
- 层次聚类
Abstract: T-distributed Stochastic Neighbor Embedding (TSNE) is introduced into cluster ensemble problem and a cluster ensemble approach based on TSNE is proposed. First, TSNE is utilized to minimize Kullback-Leibler divergences between the high-dimensinal points corresponding to the rows of hypergraphs adjacent matrix and the low-dimensional mapping points, which preserves the structure of high-dimensional space in low-dimensional space. Then, a hierarchical clustering algorithm is carried out in the low-dimensional space to obtain the final clustering result. Experimental results on several baseline datasets indicate that TSNE can improve the cluster results of hierarchical clustering algorithm and the proposed cluster ensemble method via TSNE outperforms state-of-the-art methods.
- Machine learning /
- Clustering analysis /
- Cluster ensemble /
- Hierarchical clustering

HTML全文

参考文献(21)

[1]	JAIN A K, MURTY M N, and FLYNN P J. Data clustering: A review[J]. ACM Computing Surveys, 1999, 31(3): 264-323.
[2]	JAIN A K. Data clustering: 50 years beyond K-means[J]. Pattern Recognition Letters, 2010, 31(8): 651-666.
[3]	汪晓锋, 刘功申, 李建华. 基于模糊聚类的多分辨率社区发现方法[J]. 电子与信息学报, 2017, 39(9): 2033-2039. doi: 10.11999/JEIT161116.
[4]	WANG Xiaofeng, LIU Gongshen, and LI Jianhua. Multiresolution community detection based on fuzzy clustering[J]. Journal of Electronics Information Technology, 2017, 39(9): 2033-2039. doi: 10.11999/JEIT 161116.
[5]	STREHL A and GHOSH J. Cluster ensembles: A knowledge reuse framework for combining multiple partitions[J]. Journal of Machine Learning Research, 2002, 3: 583-617.
[6]	ZHOU Zhihua and TANG Wei. Clusterer ensemble[J]. Knowledge-Based Systems, 2006, 19(1): 77-83.
[7]	罗会兰, 孔繁胜, 李一啸. 聚类集成中的差异性度量研究[J]. 计算机学报, 2007, 30(8): 1315-1323.
[8]	LUO Huilan, KONG Fansheng, and LI Yixiao. An analysis of diversity measures in clustering ensembles[J]. Chinese Journal of Computers, 2007, 30(8): 1315-1323.
[9]	WU Junjie, LIU Hongfu, XIONG Hui, et al. K-means based consensus clustering: A unified view[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(1): 155-169. doi: 10.1109/TKDE.2014.2316512.
[10]	FRED A and LOURENGO A. Cluster ensemble methods: From single clusterings to combined solutions[J]. Studies in Computational Intelligence, 2008, 126(1): 3-30.
[11]	XU Sen, CHAN Kungsic, Gao Jun, et al. An integrated K-means?Laplacian cluster ensemble approach for document datasets[J]. Neurocomputing, 2016, 214(6): 495-507. doi: 10.1016/j.neucom.2016.06.034.
[12]	YU Zhiwen, LI Le, LIU Jiming, et al. Adaptive noise immune cluster ensemble using affinity propagation[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(12): 3176-3189. doi: 10.1109/TKDE.2015.2453162.
[13]	褚睿鸿, 王红军, 杨燕, 等. 基于密度峰值的聚类集成[J]. 自动化学报, 2016, 42(9): 1401-1412. doi: 10.16383/j.aas.2016. c150864.
[14]	CHU Ruihong, WANG Hongjun, YANG Yan, et al. Clustering ensemble based on density peaks[J]. Acta Automatica Sinica, 2016, 42(9): 1401-1412. doi: 10.16383/ j.aas.2016.c150864.
[15]	BERIKOV V and PESTUNOV I. Ensemble clustering based on weighted co-association matrices: Error bound and convergence properties[J]. Pattern Recognition, 2017, 63: 427-436. doi: 10.1016/j.patcog.2016.10.017.
[16]	MAATEN L V D and HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(11): 2579-2605.
[17]	MAATEN L V D. Learning a parametric embedding by preserving local structure[C]. Proceedings of the 12th International Conference on Artificial Intelligence and Statistics, Clearwater Beach, Florida, USA, 2009: 384-391.
[18]	MAATEN L V D. Accelerating t-SNE using tree-based algorithms[J]. Journal of Machine Learning Research, 2014, 15(1): 3221-3245.
[19]	SALTON G and BUCKLEY C. Term-weighting approaches in automatic text retrieval[J]. Information Processing and Management, 1998, 24(5): 513-523.
[20]	FERN X Z and LIN W. Cluster ensemble selection[J]. Statistical Analysis Data Mining, 2008, 1(3): 128-141.
[21]	ZHAO Xingwang, LIANG Jiye, and DANG Chuangyin. Clustering ensemble selection for categorical data based on internal validity indices[J]. Pattern Recognition, 2017, 69(4): 150-168. doi: 10.1016/j.patcog.2017.04.019.

相关文章(20)

[1]	申滨, 王欣, 陈思吉, 崔太平. 基于机器学习主用户发射模式分类的蜂窝认知无线电网络频谱感知, 电子与信息学报. doi: 10.11999/JEIT191012
[2]	董道广, 芮国胜, 田文飚, 张洋, 刘歌. 具有聚类结构相似性的非参数贝叶斯字典学习算法, 电子与信息学报. doi: 10.11999/JEIT190496
[3]	张雄涛, 蒋云良, 潘兴广, 胡文军, 王士同. 基于迭代模糊聚类算法与K近邻和数据字典的集成TSK模糊分类器, 电子与信息学报. doi: 10.11999/JEIT190214
[4]	闫佳, 闫佳, 聂楚江, 苏璞睿. 基于遗传算法的恶意代码对抗样本生成方法, 电子与信息学报. doi: 10.11999/JEIT191059
[5]	侯斐斐, 施荣华, 雷文太, 董健, 许孟迪, 席景春. 面向探地雷达 B-scan图像的目标检测算法综述, 电子与信息学报. doi: 10.11999/JEIT190680
[6]	谢涛, 张春炯, 徐永健. 基于历史梯度平均方差缩减的协同参数更新方法, 电子与信息学报. doi: 10.11999/JEIT200061
[7]	赵海涛, 程慧玲, 丁仪, 张晖, 朱洪波. 基于深度学习的车联边缘网络交通事故风险预测算法研究, 电子与信息学报. doi: 10.11999/JEIT190595
[8]	陈怡, 唐迪, 邹维. 基于深度学习的Android恶意软件检测：成果与挑战, 电子与信息学报. doi: 10.11999/JEIT200009
[9]	蔡轶珩, 高旭蓉, 邱长炎, 崔益泽. 一种混合特征高效融合的视网膜血管分割方法, 电子与信息学报. doi: 10.11999/JEIT161290
[10]	邱雪松, 蔺艳斐, 邵苏杰, 郭少勇, 于军. 一种面向智能电网数据采集的传感器聚合布局构造算法, 电子与信息学报. doi: 10.11999/JEIT150231
[11]	刘家辰, 苗启广, 曹莹, 宋建锋, 权义宁. 基于混合多样性生成与修剪的集成单类分类算法, 电子与信息学报. doi: 10.11999/JEIT140161
[12]	陈志锋, 李清宝, 张平, 冯培钧. 基于聚类分析的内核恶意软件特征选择, 电子与信息学报. doi: 10.11999/JEIT150387
[13]	罗恩韬, 王国军. 大数据中一种基于语义特征阈值的层次聚类方法, 电子与信息学报. doi: 10.11999/JEIT150422
[14]	王进, 丁凌, 孙开伟, 李钟浩. 演化超网络在多类型癌症分子分型中的应用, 电子与信息学报. doi: 10.3724/SP.J.1146.2012.01171
[15]	袁志辉, 邓云凯, 李飞, 王宇, 柳罡. 改进的基于最大似然估计的多通道InSAR高程重建方法, 电子与信息学报. doi: 10.3724/SP.J.1146.2012.01530
[16]	杨景景, 苏小红, 马培军. 多层时空切片联合的快速人体跟踪算法, 电子与信息学报. doi: 10.3724/SP.J.1146.2011.01313
[17]	唐军, 裴昌幸, 苏博, 张曼君. 基于网络预测的改进型PMIPv6快速切换方法, 电子与信息学报. doi: 10.3724/SP.J.1146.2010.01272
[18]	刘锋, 徐会法, 陶然. 基于FRFT的对称三角LFMCW信号检测与参数估计, 电子与信息学报. doi: 10.3724/SP.J.1146.2010.01150
[19]	宗瑜, 李明楚, 徐贯东, 张彦春. 局部显著单元高维聚类算法, 电子与信息学报. doi: 10.3724/SP.J.1146.2009.01589
[20]	姜园, 张朝阳, 仇佩亮, 周东方. 用于数据挖掘的聚类算法, 电子与信息学报.