A Fast Logdet Divergence Based Metric Learning Algorithm for Large Data Sets Classification
Joint Authors
Mei, Jiangyuan
Hou, Jian
Chen, Jicheng
Karimi, Hamid Reza
Source
Issue
Vol. 2014, Issue 2014 (31 Dec. 2014), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2014-05-18
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
Large data sets classification is widely used in many industrial applications.
It is a challenging task to classifylarge data sets efficiently, accurately, and robustly, as large data sets always contain numerous instances with highdimensional feature space.
In order to deal with this problem, in this paper we present an online Logdet divergencebased metric learning (LDML) model by making use of the powerfulness of metric learning.
We firstly generatea Mahalanobis matrix via learning the training data with LDML model.
Meanwhile, we propose a compressedrepresentation for high dimensional Mahalanobis matrix to reduce the computation complexity in each iteration.
The final Mahalanobis matrix obtained this way measures the distances between instances accurately and serves asthe basis of classifiers, for example, the k-nearest neighbors classifier.
Experiments on benchmark data sets demonstrate that the proposed algorithm compares favorably with the state-of-the-art methods.
American Psychological Association (APA)
Mei, Jiangyuan& Hou, Jian& Chen, Jicheng& Karimi, Hamid Reza. 2014. A Fast Logdet Divergence Based Metric Learning Algorithm for Large Data Sets Classification. Abstract and Applied Analysis،Vol. 2014, no. 2014, pp.1-9.
https://search.emarefa.net/detail/BIM-1033775
Modern Language Association (MLA)
Mei, Jiangyuan…[et al.]. A Fast Logdet Divergence Based Metric Learning Algorithm for Large Data Sets Classification. Abstract and Applied Analysis No. 2014 (2014), pp.1-9.
https://search.emarefa.net/detail/BIM-1033775
American Medical Association (AMA)
Mei, Jiangyuan& Hou, Jian& Chen, Jicheng& Karimi, Hamid Reza. A Fast Logdet Divergence Based Metric Learning Algorithm for Large Data Sets Classification. Abstract and Applied Analysis. 2014. Vol. 2014, no. 2014, pp.1-9.
https://search.emarefa.net/detail/BIM-1033775
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1033775