Multi-Task Spectral Clustering by Exploring Inter-Task Correlation

Yang, Yang, Ma, Zhigang, Yang, Yi, Nie, Feiping and Shen, Heng Tao (2014) Multi-Task Spectral Clustering by Exploring Inter-Task Correlation. IEEE Transactions on Cybernetics, PP 99: 1069-1080. doi:10.1109/TCYB.2014.2344015


Author Yang, Yang
Ma, Zhigang
Yang, Yi
Nie, Feiping
Shen, Heng Tao
Title Multi-Task Spectral Clustering by Exploring Inter-Task Correlation
Journal name IEEE Transactions on Cybernetics   Check publisher's open access policy
ISSN 2168-2267
2168-2275
Publication date 2014-09-18
Year available 2014
Sub-type Article (original research)
DOI 10.1109/TCYB.2014.2344015
Open Access Status Not yet assessed
Volume PP
Issue 99
Start page 1069
End page 1080
Total pages 12
Place of publication Piscataway, NJ United States
Publisher Institute of Electrical and Electronics Engineers
Language eng
Subject 1712 Software
2207 Control and Systems Engineering
1710 Information Systems
1709 Human-Computer Interaction
1706 Computer Science Applications
2208 Electrical and Electronic Engineering
Abstract Clustering, as one of the most classical research problems in pattern recognition and data mining, has been widely explored and applied to various applications. Due to the rapid evolution of data on the Web, more emerging challenges have been posed on traditional clustering techniques: 1) correlations among related clustering tasks and/or within individual task are not well captured; 2) the problem of clustering out-of-sample data is seldom considered; and 3) the discriminative property of cluster label matrix is not well explored. In this paper, we propose a novel clustering model, namely multitask spectral clustering (MTSC), to cope with the above challenges. Specifically, two types of correlations are well considered: 1) intertask clustering correlation, which refers the relations among different clustering tasks and 2) intratask learning correlation, which enables the processes of learning cluster labels and learning mapping function to reinforce each other. We incorporate a novel ℓ-norm regularizer to control the coherence of all the tasks based on an assumption that related tasks should share a common low-dimensional representation. Moreover, for each individual task, an explicit mapping function is simultaneously learnt for predicting cluster labels by mapping features to the cluster label matrix. Meanwhile, we show that the learning process can naturally incorporate discriminative information to further improve clustering performance. We explore and discuss the relationships between our proposed model and several representative clustering techniques, including spectral clustering, k-means and discriminative k-means. Extensive experiments on various real-world datasets illustrate the advantage of the proposed MTSC model compared to state-of-the-art clustering approaches.
Formatted abstract
Clustering, as one of the most classical research problems in pattern recognition and data mining, has been widely explored and applied to various applications. Due to the rapid evolution of data on the Web, more emerging challenges have been posed on traditional clustering techniques: 1) correlations among related clustering tasks and/or within individual task are not well captured; 2) the problem of clustering out-of-sample data is seldom considered; and 3) the discriminative property of cluster label matrix is not well explored. In this paper, we propose a novel clustering model, namely multitask spectral clustering (MTSC), to cope with the above challenges. Specifically, two types of correlations are well considered: 1) intertask clustering correlation, which refers the relations among different clustering tasks and 2) intratask learning correlation, which enables the processes of learning cluster labels and learning mapping function to reinforce each other. We incorporate a novel ℓ₂,p-norm regularizer to control the coherence of all the tasks based on an assumption that related tasks should share a common low-dimensional representation. Moreover, for each individual task, an explicit mapping function is simultaneously learnt for predicting cluster labels by mapping features to the cluster label matrix. Meanwhile, we show that the learning process can naturally incorporate discriminative information to further improve clustering performance. We explore and discuss the relationships between our proposed model and several representative clustering techniques, including spectral clustering, k-means and discriminative k-means. Extensive experiments on various real-world datasets illustrate the advantage of the proposed MTSC model compared to state-of-the-art clustering approaches.
Keyword Clustering
multitask
out-of-sample
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: Official 2015 Collection
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 40 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 40 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 10 Mar 2015, 01:13:32 EST by Dr Heng Tao Shen on behalf of School of Information Technol and Elec Engineering