ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2017, Vol. 54 ›› Issue (8): 1713-1723.doi: 10.7544/issn1000-1239.2017.20170175

所属专题: 2017人工智能前沿进展专题

• 人工智能 • 上一篇    下一篇

多视角生成模型的可解释性聚类

潘笑颜,娄铮铮,姬波,叶阳东   

  1. (郑州大学信息工程学院 郑州 450001) (panxiaoyan@gs.zzu.edu.cn)
  • 出版日期: 2017-08-01
  • 基金资助: 
    国家自然科学基金项目(61502434,61170223);河南省科技攻关项目(172102210011)

Interpretable Clustering with Multi-View Generative Model

Pan Xiaoyan, Lou Zhengzheng, Ji Bo, Ye Yangdong   

  1. (School of Information Engineering Zhengzhou University, Zhengzhou 450001)
  • Online: 2017-08-01

摘要: 针对聚类中的多视角和可解释的问题,提出多视角生成模型的可解释性聚类算法(interpretable clustering with multi-view generative model, ICMG).ICMG能够产生多个视角的聚类划分,并通过视角的语义信息对聚类结果进行定性和定量地解释.首先,构建一种多视角生成模型(multi-view generative model, MGM),该模型使用贝叶斯程序学习(Bayesian program learning, BPL)和嵌入多视角因素的贝叶斯案例模型(multi-view Bayesian case model, MBCM)生成多个视角.其次,基于视角的匹配度进行聚类得到多种聚类方案.最后使用视角的原型和子空间所附带的语义信息定性和定量地解释聚类结果.实验结果表明:ICMG能够得到多种可解释的聚类结果,相比于传统多视角聚类算法具有较明显的优势.

关键词: 贝叶斯程序学习, 贝叶斯案例模型, 可解释, 多视角, 聚类

Abstract: Clustering has two problems: multi-view and interpretation. In this paper, we propose an interpretable clustering with multi-view generative model (ICMG). ICMG can get multiple clustering based multi-view meanwhile qualitatively and quantitatively interpret clustering results by using semantic information in views. Firstly, we construct a multi-view generative model (MGM). It generates multiple views by using Bayesian program learning (BPL) and multi-view Bayesian case model (MBCM). Then we get multiple clustering by clustering based on views’ matching degree. Finally, ICMG qualitatively and quantitatively interprets clustering results by using semantic information in views’ prototypes and important features. Experimental results show ICMG can get multiple interpretable clustering and the performance of ICMG is superior to traditional multi-view clustering.

Key words: Bayesian program learning (BPL), Bayesian case model (BCM), interpretable, multi-view, clustering

中图分类号: