Deflation-based power iteration clustering

Authors:
Anh Pham The;Nguyen Duc Thang;La The Vinh;Young-Koo Lee;Sungyoung Lee
Affiliations:
Department of Computer Engineering, Kyung Hee University, Yongin-si, South Korea 446-701;Department of Biomedical Engineering, International University, Ho Chi Minh City, Vietnam;Department of Computer Engineering, Kyung Hee University, Yongin-si, South Korea 446-701;Department of Computer Engineering, Kyung Hee University, Yongin-si, South Korea 446-701;Department of Computer Engineering, Kyung Hee University, Yongin-si, South Korea 446-701
Venue:
Applied Intelligence
Year:
2013

Citing 22
Cited 0

Deflation Techniques for an Implicitly Restarted Arnoldi Iteration

SIAM Journal on Matrix Analysis and Applications
An empirical comparison of four initialization methods for the K-Means algorithm

Pattern Recognition Letters
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Spectral Grouping Using the Nyström Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dominant Sets and Pairwise Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Nyström Method for Approximating a Gram Matrix for Improved Kernel-Based Learning

The Journal of Machine Learning Research
A tutorial on spectral clustering

Statistics and Computing
Improved Nyström low-rank approximation and error analysis

Proceedings of the 25th international conference on Machine learning
Density-weighted nyström method for computing large kernel eigensystems

Neural Computation
Exploiting Wikipedia as external knowledge for document clustering

Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Fast approximate spectral clustering

Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods

Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods
Data clustering: 50 years beyond K-means

Pattern Recognition Letters
Clustering social networks

WAW'07 Proceedings of the 5th international conference on Algorithms and models for the web-graph
Accelerating spectral clustering with partial supervision

Data Mining and Knowledge Discovery
Enabling scalable spectral clustering for image segmentation

Pattern Recognition
A Very Fast Method for Clustering Big Text Datasets

Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Rare Category Characterization

ICDM '10 Proceedings of the 2010 IEEE International Conference on Data Mining
Fast affinity propagation clustering: A multilevel approach

Pattern Recognition
On the equivalence between nonnegative tensor factorization and tensorial probabilistic latent semantic analysis

Applied Intelligence
Automatic MR brain image segmentation using a multiseed based multiobjective clustering approach

Applied Intelligence
Vector quantization based approximate spectral clustering of large datasets

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Spectral clustering (SC) is currently one of the most popular clustering techniques because of its advantages over conventional approaches such as K-means and hierarchical clustering. However, SC requires the use of computing eigenvectors, making it time consuming. To overcome this limitation, Lin and Cohen proposed the power iteration clustering (PIC) technique (Lin and Cohen in Proceedings of the 27th International Conference on Machine Learning, pp. 655---662, 2010), which is a simple and fast version of SC. Instead of finding the eigenvectors, PIC finds only one pseudo-eigenvector, which is a linear combination of the eigenvectors in linear time. However, in certain critical situations, using only one pseudo-eigenvector is not enough for clustering because of the inter-class collision problem. In this paper, we propose a novel method based on the deflation technique to compute multiple orthogonal pseudo-eigenvectors (orthogonality is used to avoid redundancy). Our method is more accurate than PIC but has the same computational complexity. Experiments on synthetic and real datasets demonstrate the improvement of our approach.