摘要
在实时应用中,观测样本通常以数据块的形式依次达到,传统的批量距离算法难以进行学习.本文提出一种新颖的利用成对约束关系进行学习的块增量距离尺度算法.首先给出块增量学习的一般模型,并通过扩展约束集克服其容易"过拟合"的缺陷;然后引入流形正则项使得学习过程中数据块的局部邻域结构得以保持.实验结果表明,本文算法学习的距离尺度在测试精度、计算开销上优于现有的增量距离算法,并且在存储开销方面显著优于批量距离算法.
In many real-time applications,observed samples always arrive in the form of chunks stream,traditional batch distance metric algorithms can hardly work well in such scenarios.This paper proposes a novel semi-supervised chunk incremental metric learning algorithm on the basis of the pairwise constraints.One general model is given to learn metric incrementally on the arriving chunks at first with its limitation of over-fitting overcame by utilizing extended constraint sets.Then,a manifold regularization term is used to keep locality adjacency structure of chunks during metric learning.Experimental results indicate superiorities of our algorithm,which obtains better accuracy and lower computation costs than existing incremental metric learning algorithms,and needs much less storage costs than batch ones.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2011年第5期1131-1135,共5页
Acta Electronica Sinica
基金
教育部人文社会科学研究青年基金(No.10YJCZH153)
西南财经大学"211工程"三期青年教师成长项目(No.211QN09028)
关键词
距离尺度学习
半监督
块增量学习
流形正则
distance metric learning
semi-supervised
chunk incremental learning
manifold regularization
