[1]杨文元.多标记学习自编码网络无监督维数约简[J].智能系统学报,2018,13(05):808-817.[doi:10.11992/tis.201804051]
 YANG Wenyuan.Unsupervised dimensionality reduction of multi-label learning via autoencoder networks[J].CAAI Transactions on Intelligent Systems,2018,13(05):808-817.[doi:10.11992/tis.201804051]
点击复制

多标记学习自编码网络无监督维数约简(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第13卷
期数:
2018年05期
页码:
808-817
栏目:
出版日期:
2018-09-05

文章信息/Info

Title:
Unsupervised dimensionality reduction of multi-label learning via autoencoder networks
作者:
杨文元
闽南师范大学 福建省粒计算及其应用重点实验室, 福建 漳州 363000
Author(s):
YANG Wenyuan
Fujian Key Laboratory of Granular Computing and Application, Minnan Normal University, Zhangzhou 363000, China
关键词:
多标记学习维数约简无监督学习神经网络自编码器机器学习深度学习特征提取
Keywords:
multi-label learningdimensionality reductionunsupervised learningneural networksautoencodermachine learningdeep learningfeature extraction
分类号:
TP183
DOI:
10.11992/tis.201804051
摘要:
多标记学习是针对一个实例同时与一组标签相关联而提出的一种机器学习框架,是该领域研究热点之一,降维是多标记学习一个重要且具有挑战性的工作。针对有监督的多标记维数约简方法,提出一种无监督自编码网络的多标记降维方法。首先,通过构建自编码神经网络,对输入数据进行编码和解码输出;然后,引入稀疏约束计算总体成本,使用梯度下降法进行迭代求解;最后,通过深度学习训练获得自编码网络学习模型,提取数据特征实现维数约简。实验中使用多标记算法ML-kNN做分类器,在6个公开数据集上与其他4种方法对比。实验结果表明,该方法能够在不使用标记的情况下有效提取特征,降低多标记数据维度,稳定提高多标记学习性能。
Abstract:
Multi-label learning is a machine learning framework that simultaneously deals with data associated with a group of labels. It is one of the hot spots in the field of machine learning. However, dimensionality reduction is a significant and challenging task in multi-label learning. In this paper, we propose a unsupervised dimensionality reduction method for supervised multi-label dimensiona reduction methods via autoencoder networks. Firstly, we build the autoencoder neural network to encode the input data and then decode them for output. Then we introduce the sparse constraint to calculate the overall cost, and further use the gradient descent method to iterate them. Finally, we obtain the autoencoder network learning model by deep learning training, and then extract data features to reduce dimensionality. In the experiments, we use a multi-label algorithm (ML-kNN) as the classifier, and compare them with four other methods on six publicly available datasets. Experimental results show that the proposed method can effectively extract features without using label learning; thus, it reduces multi-label data dimensionality and steadily improves the performance of multi-label learning.

参考文献/References:

[1] ZHANG Minling, ZHOU Zhihua. A review on multi-Label learning algorithms[J]. IEEE transactions on knowledge and data engineering, 2014, 26(8):1819-1837.
[2] TSOUMAKAS G, KATAKIS I. Multi-label classification:an overview[J]. International journal of data warehousing and mining, 2007, 3(3):1-13.
[3] WU Fei, WANG Zhuhao, ZHANG Zhongfei, et al. Weakly semi-supervised deep learning for multi-label image annotation[J]. IEEE transactions on big data, 2015, 1(3):109-122.
[4] LI Feng, MIAO Duoqian, PEDRYCZ W. Granular multi-label feature selection based on mutual information[J]. Pattern recognition, 2017, 67:410-423.
[5] ZHANG Yin, ZHOU Zhihua. Multilabel dimensionality reduction via dependence maximization[J]. ACM transactions on knowledge discovery from data, 2010, 4(3):1-21.
[6] 郭雨萌, 李国正. 一种多标记数据的过滤式特征选择框架[J]. 智能系统学报, 2014, 9(3):292-297 GUO Yumeng, LI Guozheng. A filtering framework fro the multi-label feature selection[J]. CAAI transactions on intelligent systems, 2014, 9(3):292-297
[7] JINDAL P, KUMAR D. A review on dimensionality reduction techniques[J]. International journal of computer applications, 2017, 173(2):42-46.
[8] OMPRAKASH S, SUMIT S. A review on dimension reduction techniques in data mining[J]. Computer engineering and intelligent systems, 2018, 9(1):7-14.
[9] YU Tingzhao, ZHANG Wensheng. Semisupervised multilabel learning with joint dimensionality reduction[J]. IEEE signal processing letters, 2016, 23(6):795-799.
[10] YU Yanming, WANG Jun, TAN Qiaoyu, et al. Semi-supervised multi-label dimensionality reduction based on dependence maximization[J]. IEEE access, 2017, 5:21927-21940.
[11] ZHANG Minling, ZHANG Kun. Multi-label learning by exploiting label dependency[C]//Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington, DC, USA, 2010:999-1008.
[12] ZHANG Minling, ZHOU Zhihua. ML-KNN:a lazy learning approach to multi-label learning[J]. Pattern recognition, 2007, 40(7):2038-2048.
[13] BALDI P. Autoencoders, unsupervised learning and deep architectures[C]//Proceedings of the 2011 International Conference on Unsupervised and Transfer Learning Workshop. Washington, USA, 2011:37-50.
[14] BOURLARD H, KAMP Y. Auto-association by multilayer perceptrons and singular value decomposition[J]. Biological cybernetics, 1988, 59(4/5):291-294.
[15] 刘帅师, 程曦, 郭文燕, 等. 深度学习方法研究新进展[J]. 智能系统学报, 2016, 11(5):567-577 LIU Shuaishi, CHENG Xi, GUO Wenyan, et al. Progress report on new research in deep learning[J]. CAAI transactions on intelligent systems, 2016, 11(5):567-577
[16] VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J]. Journal of machine learning research, 2010, 11(12):3371-3408.
[17] YU Ying, WANG Yinglong. Feature selection for multi-label learning using mutual information and GA[M]//MIAO D, PEDRYCZ W, SLEZAK D, et al. Rough Sets and Knowledge Technology. Cham:Springer, 2014:454-463.
[18] 余鹰. 多标记学习研究综述[J]. 计算机工程与应用, 2015, 51(17):20-27 YU Ying. Survey on multi-label learning[J]. Computer engineering and applications, 2015, 51(17):20-27
[19] 段洁, 胡清华, 张灵均, 等. 基于邻域粗糙集的多标记分类特征选择算法[J]. 计算机研究与发展, 2015, 52(1):56-65 DUAN Jie, HU Qinghua, ZHANG Lingjun, et al. Feature selection for multi-label classification based on neighborhood rough sets[J]. Journal of computer research and development, 2015, 52(1):56-65
[20] DOQUIRE G, VERLEYSEN M. Feature selection for multi-label classification problems[C]//Proceedings of the 11th International Conference on Artificial Neural NetWorks Conference on Advances in Computational Intelligence. Torremolinos-Mÿlaga, Spain, 2011:9-16.
[21] LAMDA. Data & Code[EB/OL]. Nanjing:LAMDA, 2016[2018.03.20]. http://lamda.nju.edu.cn/Data.ashx.
[22] WOLD S, ESBENSEN K, GELADI P. Principal component analysis[J]. Chemometrics and intelligent laboratory systems, 1987, 2(1):27-52.
[23] HE Xiaofei. Locality preserving projections[M]. IL, USA:University of Chicago, 2005:186-197.
[24] BELKIN M, NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural computation, 2003, 15(6):1373-1396.
[25] SCHAPIRE R E, SINGER Y. Boos texter:a boosting-based systemfor text categorization[J]. Machine learning-special issue on information retrieval, 2000, 39(2/3):135-168.
[26] TSOUMAKAS G, VLAHAVAS I. Random k-labelsets:an ensemble method for multilabel classification[M]//KOK J N, KORONACKI J, MANTARAS R L, et al. Machine Learning:ECML 2007. Berlin Heidelberg:Springer, 2007:406-417.

相似文献/References:

[1]徐 蓉,姜 峰,姚鸿勋.流形学习概述[J].智能系统学报,2006,1(01):44.
 XU Rong,JIANG Feng,YAO Hong-xun.Overview of manifold learning[J].CAAI Transactions on Intelligent Systems,2006,1(05):44.
[2]刘杨磊,梁吉业,高嘉伟,等.基于Tri-training的半监督多标记学习算法[J].智能系统学报,2013,8(05):439.[doi:10.3969/j.issn.1673-4785.201305033]
 LIU Yanglei,LIANG Jiye,GAO Jiawei,et al.Semi-supervised multi-label learning algorithm based on Tri-training[J].CAAI Transactions on Intelligent Systems,2013,8(05):439.[doi:10.3969/j.issn.1673-4785.201305033]

备注/Memo

备注/Memo:
收稿日期:2018-04-25。
基金项目:国家自然科学青年基金项目(61703196);福建省自然科学基金项目(2018J01549).
作者简介:杨文元,男,1967年生,副教授,博士,主要研究方向为机器学习、多标记学习、模式识别、计算机视觉。发表学术论文20余篇。
通讯作者:杨文元.Email:yangwy@mnnu.edu.cn.
更新日期/Last Update: 2018-10-25