[1]郭瑛洁,王士同,许小龙.基于最大间隔理论的组合距离学习算法[J].智能系统学报编辑部,2015,(6):843-850.[doi:10.11992/tis.201504027]
 GUO Yingjie,WANG Shitong,XU Xiaolong.Learning a linear combination of distances based on the maximum-margin theory[J].CAAI Transactions on Intelligent Systems,2015,(6):843-850.[doi:10.11992/tis.201504027]
点击复制

基于最大间隔理论的组合距离学习算法(/HTML)
分享到:

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

卷:
期数:
2015年6期
页码:
843-850
栏目:
出版日期:
2015-12-25

文章信息/Info

Title:
Learning a linear combination of distances based on the maximum-margin theory
作者:
郭瑛洁 王士同 许小龙
江南大学数字媒体学院, 江苏无锡 214000
Author(s):
GUO Yingjie WANG Shitong XU Xiaolong
School of Digital Media, Jiangnan University, Wuxi 214000, China
关键词:
距离学习组合距离最大间隔FCM模糊聚类聚类算法距离学习算法
Keywords:
metric learninghybrid distance metricmaximum-margin theoryfuzzy C-meansfuzzy clusteringclustering algorithmmetriclearning algorithm
分类号:
TP181
DOI:
10.11992/tis.201504027
摘要:
从已知数据集中学习距离度量在许多机器学习应用中都起着重要作用。传统的距离学习方法通常假定目标距离函数为马氏距离的形式,这使得学习出的距离度量在应用上具有局限性。提出了一种新的距离学习方法,将目标距离函数表示为若干候选距离的线性组合,依据最大间隔理论利用数据集的边信息学习得到组合距离中各距离分量的权值,从而得到新的距离度量。通过该距离度量在模糊C均值聚类算法中的表现来对其进行评价。在UCI数据集上,与其他已有的距离学习算法的对比实验结果证明了该文算法的有效性。
Abstract:
Learning a distance metric from given training samples is a crucial aspect of many machine learning tasks. Conventional distance metric learning approaches often assume the target distance function to be represented in the form of Mahalanobis distance, and the metric has limitations for this application. This paper proposes a new metric learning approach in which the target distance function is represented as a linear combination of several candidate distance metrics. This method obtains a new distance metric by learning weights from side information according to the maximum-margin theory. The new distance function is applied to fuzzy C-means clustering for evaluation. The experiments were performed using UCI data, and a comparison of the results with those of other approaches reveals the advantages of the proposed technique.

参考文献/References:

[1] 王骏, 王士同. 基于混合距离学习的双指数模糊C均值算法[J]. 软件学报, 2010, 21(8):1878-1888. WANG Jun, WANG Shitong. Double indices FCM algorithm based on hybrid distance metric learning[J]. Journal of Software, 2010, 21(8):1878-1888.
[2] WU Lei, HOI S C H, JIN Rong, et al. Learning Bregman distance functions for semi-supervised clustering[J]. IEEE Transactions on Knowledge and Data Engineering, 2012, 24(3):478-491.
[3] XING E P, NG A Y, JORDAN M I, et al. Distance metric learning with application to clustering with side information[C]//Advances in Neural Information Processing Systems. Vancouver, Canada, 2002:521-528.
[4] HOI S C H, LIU Wei, LYU M R, et al. Learning distance metrics with contextual constraints for image retrieval[C]//Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, America, 2006, 2:2072-2078.
[5] GOLDBERGER J, HINTON G, ROWEIS S, et al. Neighborhood component analysis[C]//Advances in Neural Information Processing Systems. Cambridge, United Kingdom, 2005:451-458.
[6] WEINBERGER K Q, BLITZER J C, SAUL L K. Distance metric learning for large margin nearest neighbor classification[C]//Advances in Neural Information Processing Systems. Cambridge, United Kingdom, 2006:1473-1480.
[7] 王骏, 王士同, 邓赵红. 特征加权距离与软子空间学习相结合的文本聚类新方法[J]. 计算机学报, 2012, 35(8):1655-1665. WANG Jun, WANG Shitong, DENG Zhaohong. A novel text clustering algorithm based on feature weighting distance and soft subspace learning[J]. Chinese Journal of Computers, 2012, 35(8):1655-1665.
[8] WU K L, YANG M S. Alternative c-means clustering algorithms[J]. Pattern Recognition, 2002, 35(10):2267-2278.
[9] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[10] TSANG I W H, KWOK J T Y, ZURADA J A. Generalized Core Vector Machines[J]. IEEE Transaction on Neural Networks, 2006, 17(5):1126-1140.
[11] MEI Jianping, CHEN Lihui. Fuzzy clustering with weighted medoids for relational data[J]. Pattern Recognition, 2010, 43(5):1964-1974.
[12] WAGSTAFF K, CARDIE C, ROGERS S, et al. Constrained k-means clustering with background knowledge[C]//BAR-HILLEL A, HERTZ T, SHENTAL N, et al. Proceedings of the Eighteenth International Conference on Machine Learning. Williamstown, Australia,2001:577-584.
[13] COVÕES T F, HRUSCHKA E R, GHOSH J. A study of k-means-based algorithms for constrained clustering[J]. Intelligent Data Analysis, 2013, 17(3):485-505.
[14] BEZDEK J C. Pattern recognition with fuzzy objective function algorithms[M]. New York:Plenum Press, 1981:56-57.

相似文献/References:

[1]仝伯兵,王士同,梅向东.稀疏条件下的两层分类算法[J].智能系统学报编辑部,2015,(01):27.[doi:10.3969/j.issn.1673-4785.201407019]
 TONG Bobing,WANG Shitong,MEI Xiangdong.Sparsity-inspired two-level classification algorithm[J].CAAI Transactions on Intelligent Systems,2015,(6):27.[doi:10.3969/j.issn.1673-4785.201407019]

备注/Memo

备注/Memo:
收稿日期:2015-04-19;改回日期:。
基金项目:国家自然科学基金资助项目(61272210);江苏省自然科学基金资助项目(BK2011417,BK2011003).
作者简介:郭瑛洁,女,1991生,硕士研究生,主要研究方向为人工智能、模式识别。王士同,男,1964生,教授,博士生导师,主要研究方向为人工智能、模式识别和生物信息。许小龙,男,1989生,硕士研究生,主要研究方向为人工智能、模式识别。
通讯作者:郭瑛洁.E-mail:ying_dm@163.com.
更新日期/Last Update: 1900-01-01