Sample-Weighted Multi-View Clustering

被引：0
|
作者：
Hong M. [1 ,2 ]
Jia C. [1 ,2 ]
Li Y. [3 ]
Yu J. [1 ,2 ]
机构：
[1] Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing
[2] School of Computer and Information Technology, Beijing Jiaotong University, Beijing
[3] Faculty of Information Technology, Beijing University of Technology, Beijing
来源：
Jisuanji Yanjiu yu Fazhan/Computer Research and Development | 2019年 / 56卷 / 08期
基金：
中国国家自然科学基金;
关键词：
Cluster; Data mining; K-means; Multi-view; Sample weights;
D O I：
10.7544/issn1000-1239.2019.20190150
中图分类号：
学科分类号：
摘要：
In the era of big data, the ability of humans to collect, store, transmit and manage data has been increasingly improved. Various industries have accumulated a large amount of data resources, which are often multi-source and heterogeneous. How to effectively cluster these multi-source data (also known as multi-view clustering) has become one of the focuses of today's machine learning research. The existing multi-view clustering algorithms mainly pay attention to the contribution of different views and features to the cluster structure from the "global" perspective, without considering the "local" information complementary differences between different samples. Therefore, this paper proposes a new sample-weighted multi-view clustering (SWMVC). The method weights each sample with different views and adopts alternating direction method of multipliers (ADMM) to learn sample weight, which can not only learn the "local" difference of weights among multiple views in different sample points, but also reflect the "global" difference of the contribution of different views to the cluster structure, and has better flexibility. Experiments on multiple datasets show that the SWMVC method has a better clustering effect on heterogeneous view data. © 2019, Science Press. All right reserved.
引用
下载
收藏
页码：1677 / 1685
页数：8
相关论文
共 17 条
  • [1] Yarowsky D., Unsupervised word sense disambiguation rivaling supervised methods, Proc of the 33rd Annual Meeting on Association for Computational Linguistics, pp. 189-196, (1995)
  • [2] Blum A., Mitchell T., Combining labeled and unlabeled data with co-training, Proc of the 11th Annual Conf on Computational Learning Theory, pp. 92-100, (1998)
  • [3] Bickel S., Scheffer T., Multi-view clustering, Proc of the 4th IEEE Int Conf on Data Mining, pp. 19-26, (2004)
  • [4] Cleuziou G., Exbrayat M., Martin L., Et al., CoFKM: A centralized method for multiple-view clustering, Proc of the 9th IEEE Int Conf on Data Mining, pp. 752-757, (2009)
  • [5] De Sa V.R., Spectral clustering with two views, Proc of the Workshop on Learning with Multiple Views, pp. 20-27, (2005)
  • [6] Kumar A., Daume H., A co-training approach for multi-view spectral clustering, Proc of the 28th Int Conf on Machine Learning, pp. 393-400, (2011)
  • [7] Kumar A., Rai P., Daume H., Co-regularized multi-view spectral clustering, Proc of the 24th Int Conf on Neural Information Processing System, pp. 1413-1421, (2011)
  • [8] Tzortzis G.F., Likas A.C., Multiple view clustering using a weighted combination of exemplar-based mixture models, IEEE Transactions on Neural Networks, 21, 12, pp. 1925-1938, (2010)
  • [9] Tzortzis G., Likas A., Kernel-Based Weighted Multi-view Clustering, Proc of the 12th IEEE Int Conf on Data Mining, pp. 675-684, (2012)
  • [10] Cai X., Nie F., Huang H., Multi-view K-means clustering on big data, Proc of the 23rd Int Joint Conf on Artificial Intelligence, pp. 2598-2604, (2013)
12