Browse > Article
http://dx.doi.org/10.4218/etrij.16.0115.0517

Robust Similarity Measure for Spectral Clustering Based on Shared Neighbors  

Ye, Xiucai (Department of Computer Science, University of Tsukuba)
Sakurai, Tetsuya (Department of Computer Science, University of Tsukuba)
Publication Information
ETRI Journal / v.38, no.3, 2016 , pp. 540-550 More about this Journal
Abstract
Spectral clustering is a powerful tool for exploratory data analysis. Many existing spectral clustering algorithms typically measure the similarity by using a Gaussian kernel function or an undirected k-nearest neighbor (kNN) graph, which cannot reveal the real clusters when the data are not well separated. In this paper, to improve the spectral clustering, we consider a robust similarity measure based on the shared nearest neighbors in a directed kNN graph. We propose two novel algorithms for spectral clustering: one based on the number of shared nearest neighbors, and one based on their closeness. The proposed algorithms are able to explore the underlying similarity relationships between data points, and are robust to datasets that are not well separated. Moreover, the proposed algorithms have only one parameter, k. We evaluated the proposed algorithms using synthetic and real-world datasets. The experimental results demonstrate that the proposed algorithms not only achieve a good level of performance, they also outperform the traditional spectral clustering algorithms.
Keywords
Spectral clustering; data analysis; similarity measure; shared nearest neighbors; directed kNN graph;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 U. Von Luxburg, "A Tutorial on Spectral Clustering," Statistics Comput., vol. 17, no. 4, Dec. 2007, pp. 395-416.   DOI
2 J. Malik et al., "Contour and Texture Analysis for Image Segmentation," Int. J. Comput. Vision, vol. 43, no. 1, June 2001, pp. 7-27.   DOI
3 B. Hendrickson and R. Leland, "An Improved Spectral Graph Partitioning Algorithm for Mapping Parallel Computations," SIAM J. Scientific Comput., vol. 16, no. 2, 1995, pp. 452-469.   DOI
4 W. Hu et al., "Semantic Based Surveillance Video Retrieval," IEEE Trans. Image Process., vol. 16, no. 4, 2007, pp. 1168-1181.   DOI
5 Z. Yu et al., "Sc3: Triple Spectral Clustering Based Consensus Clustering Framework for Class Discovery from Cancer Gene Expression Profiles," IEEE/ACM Trans. Comput. Biology Bioinfomatics, vol. 9, no. 6, Dec. 2012, pp. 1751-1765.   DOI
6 A.Y. Ng, M.I. Jordan, and Y. Weiss, "On Spectral Clustering: Analysis and an Algorithm," NIPS Proc., 2001, pp. 849-856.
7 L. Zelnik-Manor and P. Perona, "Self-Tuning Spectral Clustering," NIPS Proc., 2004, pp. 1601-1608.
8 H. Chang and D. Yeung, "Robust Path-Based Spectral Clustering," Pattern Recogn., vol. 41, no. 1, 2008, pp. 191-203.   DOI
9 X. Zhang, J. Li, and H. Yu, "Local Density Adaptive Similarity Measurement for Spectral Clustering," Pattern Recogn. Lett., vol. 32, no. 2, Jan. 2011, pp. 352-358.   DOI
10 X. He, S. Zhang, and Y. Liu, "An Adaptive Spectral Clustering Algorithm Based on the Importance of Shared Nearest Neighbors," Algorithms, vol. 8, no. 2, May 2015, pp. 177-189.   DOI
11 J. Cao et al., "A Max-Flow-Based Similarity Measure for Spectral Clustering," ETRI J., vol. 35, no. 2, Apr. 2013, pp. 311-320.   DOI
12 M. Lucinska and S.T. Wierzchon, "Spectral Clustering Based on k-Nearest Neighbor Graph," Lecture Notes Comput. Sci., vol. 7564, 2012, pp. 254-265.
13 R.A. Jarvis and E.A. Patrick, "Clustering Using a Similarity Measure Based on Shared Near Neighbors," IEEE Trans. Comput., vol. C-22, no. 11, Nov. 1973, pp. 1025-1034.   DOI
14 L. Ertoz, M. Steinbach, and V. Kumar, "Finding Clusters of Different Sizes, Shapes, and Densities in Noisy, High Dimensional Data," Proc. SIAM Int. Conf. Data Mining, San Francisco, CA, USA, May 1-3, 2003, pp. 47-58.
15 M.E. Houle et al., "Can Shared-Neighbor Distances Defeat the Curse of Dimensionality?" Lecture Notes Comput. Sci., vol. 6187, 2010, pp. 482-500.
16 M. Beauchemin, "A Density-Based Similarity Matrix Construction for Spectral Clustering," Neurocomputing, Mar. 2015, pp. 835-844.   DOI
17 X. Zhu, C.C. Loy, and S. Gong, "Constructing Robust Affinity Graphs for Spectral Clustering," IEEE Conf. Computer Vision Patten Recogn., Columbus, OH, USA, June 23-28, 2014, pp. 1450-1457.
18 C. Fowlkes et al., "Spectral Grouping Using the Nystrom Method," IEEE Trans. Pattern Anal.. Mach. Intell., vol. 26, no. 2, Feb. 2004, pp. 214-225.   DOI
19 H. Wang, J. Chen, and K. Guo, "A Genetic Spectral Clustering Algorithm," Int. J. Comput. Inf. Syst., vol. 7, no. 9, 2011, pp. 3245-3252.
20 H.D. Menendez, D.F. Barrero, and D. Camacho, "A Genetic Graph-Based Approach for Partitional Clustering," Int. J. Neural Syst., vol. 24, no. 3, May 2014.
21 X. Ye and T. Sakurai, "Spectral Clustering Using Robust Similarity Measure Based on Closeness of Shared Nearest Neighbors," Int. Joint Conf. Neural Netw., Killarney, Ireland, July 12-17, 2015, pp. 1-8.
22 J. McNames, "A Fast Nearest-Neighbor Algorithm Based on a Principal Axis Search Tree," IEEE Trans. Pattern Anal. Mach. Intell., vol. 23, no. 9, Sept. 2011, pp. 964-976.
23 W. Chen et al., "Parallel Spectral Clustering in Distributed Systems," IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 3, Mar. 2011, pp. 568-586.   DOI
24 A. Strehl and J. Ghosh, "Cluster Ensembles: A Knowledge Reuse Framework for Combining Multiple Partitions," J. Mach. Learn. Research, vol. 3, Mar. 2003, pp. 583-617.
25 UCI Machine Learning Repository, Accessed Mar. 1, 2015. http://archive.ics.uci.edu/ml/
26 Y. Lwcun, C. Cortes, and J.C. Burges, The MNIST Database of Handwritten Digits, Accessed Mar. 1, 2015. http://yann.lecun.com/exdb/mnist/
27 S. Nene, S. Nayar, and J. Murase, Columbia Object Image Library (COIL-20), Dept. Comp. Sci., Columbia Univ., New York, Tech. Rep. CUCS-005-96, 1996.
28 Yale Face Database, Accessed Mar. 1, 2015. http://vision.ucsd.edu/content/yale-facedatabase