Multi-view learning via probabilistic latent semantic analysis

Multi-view learning via probabilistic latent semantic analysis
复制标题

通过概率潜在语义分析进行多视图学习

DOI:
10.1016/j.ins.2012.02.058
复制
发表时间:
2012-09
影响因子:
8.1
通讯作者:
Shi Zhongzhi
Shi Zhongzhi
中科院分区:
计算机科学1区
文献类型:
--
作者:
Karypis George;Ning Xia;He Qing;Shi Zhongzhi

文献摘要

参考文献

被引文献

相似文献

在过去的几十年里,多视角学习由于在网页分析、生物信息学、图像处理等领域的大量实际应用而引起了人们的极大兴趣。不同于以往大多数工作遵循协同训练的思想,本文提出了一种新的基于概率潜在语义分析的多视点学习产生式模型,称为MVPLSA。在该模型中,我们从不同的视图对特征和文档的共现进行联合建模。具体地说,在该模型中,潜在主题有两个潜在变量y,文档簇有两个潜在变量z,文档有三个可见变量d,特征有f,视图标签有v。利用与v无关的条件概率p(z|d)作为多视点间知识共享的桥梁。此外,我们有依赖于v的p(y|z,v)和p(f|y,v)来捕获每个视图中的特定结构。在四个真实数据集上进行了实验,验证了该模型的有效性和优越性。
Multi-view learning arouses vast amount of interest in the past decades with numerous real-world applications in web page analysis, bioinformatics, image processing and so on. Unlike the most previous works following the idea of co-training, in this paper we propose a new generative model for Multi-view Learning via Probabilistic Latent Semantic Analysis, called MVPLSA. In this model, we jointly model the co-occurrences of features and documents from different views. Specifically, in the model there are two latent variables y for the latent topic and z for the document cluster, and three visible variables d for the document, f for the feature, and v for the view label. The conditional probability p(z∣d), which is independent of v, is used as the bridge to share knowledge among multiple views. Also, we have p(y∣z, v) and p(f∣y, v), which are dependent of v, to capture the specifical structures inside each view. Experiments are conducted on four real-world data sets to demonstrate the effectiveness and superiority of our model.
DOI: 10.1109/icassp.2009.4959893
发表时间: 2009-04
期刊: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
影响因子: --
作者:
Jiho Yoo;Seungjin Choi
通讯作者: Jiho Yoo;Seungjin Choi
DOI: 10.1007/s13042-011-0026-z
发表时间: 2011-07
影响因子: 5.6
作者:
Julio J. Castillo
通讯作者: Julio J. Castillo
DOI: 10.1016/j.ins.2010.06.021
发表时间: 2010-10
期刊: Inf. Sci.
影响因子: --
作者:
Wenyin Liu;Xiaojun Quan;Min Feng;B. Qiu
通讯作者: Wenyin Liu;Xiaojun Quan;Min Feng;B. Qiu
DOI: 10.1145/1871437.1871486
发表时间: 2010-10
期刊: Proceedings of the 19th ACM international conference on Information and knowledge management
影响因子: --
作者:
Fuzhen Zhuang;Ping Luo;Zhiyong Shen;Qing He;Yuhong Xiong;Zhongzhi Shi;Hui Xiong
通讯作者: Fuzhen Zhuang;Ping Luo;Zhiyong Shen;Qing He;Yuhong Xiong;Zhongzhi Shi;Hui Xiong
DOI: 10.1137/1.9781611972740.31
发表时间: 2004-06
期刊: --
影响因子: --
作者:
Sugato Basu;A. Banerjee;R. Mooney
通讯作者: Sugato Basu;A. Banerjee;R. Mooney