Density-Aware Clustering Based on Aggregated Heat Kernel and Its Transformation

Huang, Hao; Yoo, Shinjae; Yu, Dantong; Qin, Hong

doi:10.1145/2700385

Density-Aware Clustering Based on Aggregated Heat Kernel and Its Transformation

Journal Article · Mon Jun 01 04:00:00 EDT 2015 · ACM Transactions on Knowledge Discovery from Data

DOI:https://doi.org/10.1145/2700385· OSTI ID:1210172

Huang, Hao ^[1]; Yoo, Shinjae ^[2]; Yu, Dantong ^[2]; Qin, Hong ^[1]

Stony Brook Univ., NY (United States). Computer Sciences Dept.
Brookhaven National Lab. (BNL), Upton, NY (United States). Computational Science Center

Current spectral clustering algorithms suffer from the sensitivity to existing noise, and parameter scaling, and may not be aware of different density distributions across clusters. If these problems are left untreated, the consequent clustering results cannot accurately represent true data patterns, in particular, for complex real world datasets with heterogeneous densities. This paper aims to solve these problems by proposing a diffusion-based Aggregated Heat Kernel (AHK) to improve the clustering stability, and a Local Density Affinity Transformation (LDAT) to correct the bias originating from different cluster densities. AHK statistically\ models the heat diffusion traces along the entire time scale, so it ensures robustness during clustering process, while LDAT probabilistically reveals local density of each instance and suppresses the local density bias in the affinity matrix. Our proposed framework integrates these two techniques systematically. As a result, not only does it provide an advanced noise-resisting and density-aware spectral mapping to the original dataset, but also demonstrates the stability during the processing of tuning the scaling parameter (which usually controls the range of neighborhood). Furthermore, our framework works well with the majority of similarity kernels, which ensures its applicability to many types of data and problem domains. The systematic experiments on different applications show that our proposed algorithms outperform state-of-the-art clustering algorithms for the data with heterogeneous density distributions, and achieve robust clustering performance with respect to tuning the scaling parameter and handling various levels and types of noise.

View Accepted Manuscript (DOE)

Research Organization:: Brookhaven National Laboratory (BNL), Upton, NY (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Advanced Scientific Computing Research (SC-21)

OSTI ID:: 1210172

Report Number(s):: BNL--108231-2015-JA

Journal Information:: ACM Transactions on Knowledge Discovery from Data, Journal Name: ACM Transactions on Knowledge Discovery from Data Journal Issue: 4 Vol. 9; ISSN 1556-4681

Publisher:: Association for Computing MachineryCopyright Statement

Country of Publication:: United States

Language:: English

References (36)

Robust Statistics Huber, Peter J.; Ronchetti, Elvezio M. John Wiley & Sons, Inc https://doi.org/10.1002/9780470434697	book	January 2009
Vector-valued Laplace Transforms and Cauchy Problems Arendt, Wolfgang; Batty, Charles J. K.; Hieber, Matthias Monographs in Mathematics https://doi.org/10.1007/978-3-0348-0087-7	book	January 2011
A factorization approach to grouping Perona, P.; Freeman, W. Computer Vision — ECCV'98 https://doi.org/10.1007/BFb0055696	book	January 1998
A tutorial on spectral clustering von Luxburg, Ulrike Statistics and Computing, Vol. 17, Issue 4 https://doi.org/10.1007/s11222-007-9033-z	journal	August 2007
Rock: A robust clustering algorithm for categorical attributes Guha, Sudipto; Rastogi, Rajeev; Shim, Kyuseok Information Systems, Vol. 25, Issue 5 https://doi.org/10.1016/S0306-4379(00)00022-3	journal	July 2000
Diffusion maps Coifman, Ronald R.; Lafon, Stéphane Applied and Computational Harmonic Analysis, Vol. 21, Issue 1 https://doi.org/10.1016/j.acha.2006.04.006	journal	July 2006
Revised DBSCAN algorithm to cluster data with dense adjacent clusters Tran, Thanh N.; Drab, Klaudia; Daszykowski, Michal Chemometrics and Intelligent Laboratory Systems, Vol. 120 https://doi.org/10.1016/j.chemolab.2012.11.006	journal	January 2013
Spectral clustering with density sensitive similarity function Yang, Peng; Zhu, Qingsheng; Huang, Biao Knowledge-Based Systems, Vol. 24, Issue 5 https://doi.org/10.1016/j.knosys.2011.01.009	journal	July 2011
Robust path-based spectral clustering Chang, Hong; Yeung, Dit-Yan Pattern Recognition, Vol. 41, Issue 1 https://doi.org/10.1016/j.patcog.2007.04.010	journal	January 2008
Local density adaptive similarity measurement for spectral clustering Zhang, Xianchao; Li, Jingwei; Yu, Hong Pattern Recognition Letters, Vol. 32, Issue 2 https://doi.org/10.1016/j.patrec.2010.09.014	journal	January 2011
Estimates of heat kernels on Riemannian manifolds Grigor'yan, Alexander Spectral Theory and Geometry https://doi.org/10.1017/CBO9780511566165.008	book	September 1999
Chameleon: hierarchical clustering using dynamic modeling Karypis, G.; Kumar, V. Computer, Vol. 32, Issue 8 https://doi.org/10.1109/2.781637	journal	January 1999
Mean shift: a robust approach toward feature space analysis Comaniciu, D.; Meer, P. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, Issue 5 https://doi.org/10.1109/34.1000236	journal	May 2002
Noise-resistant invariants of curves Weiss, I. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, Issue 9 https://doi.org/10.1109/34.232081	journal	January 1993
Normalized cuts and image segmentation No authors listed IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, Issue 8 https://doi.org/10.1109/34.868688	journal	January 2000
Robust anisotropic diffusion Black, M. J.; Sapiro, G.; Marimont, D. H. IEEE Transactions on Image Processing, Vol. 7, Issue 3 https://doi.org/10.1109/83.661192	journal	March 1998
Robust clustering methods: a unified view Dave, R. N.; Krishnapuram, R. IEEE Transactions on Fuzzy Systems, Vol. 5, Issue 2 https://doi.org/10.1109/91.580801	journal	May 1997
Noise Robust Spectral Clustering Li, Zhenguo; Liu, Jianzhuang; Chen, Shifeng 2007 IEEE 11th International Conference on Computer Vision https://doi.org/10.1109/ICCV.2007.4409061	conference	January 2007
A Robust Clustering Algorithm Based on Aggregated Heat Kernel Mapping Huang, Hao; Yoo, Shinjae; Qin, Hong 2011 IEEE 11th International Conference on Data Mining https://doi.org/10.1109/ICDM.2011.15	conference	December 2011
Robust Support Vector Regression for Biophysical Variable Estimation From Remotely Sensed Images Camps-Valls, G.; Bruzzone, L.; Rojo-Rojo, J. L. IEEE Geoscience and Remote Sensing Letters, Vol. 3, Issue 3 https://doi.org/10.1109/LGRS.2006.871748	journal	July 2006
Clustering Using a Similarity Measure Based on Shared Near Neighbors Jarvis, R. A.; Patrick, E. A. IEEE Transactions on Computers, Vol. C-22, Issue 11 https://doi.org/10.1109/T-C.1973.223640	journal	November 1973
Multiple Model Regression Estimation Cherkassky, V.; Ma, Y. IEEE Transactions on Neural Networks, Vol. 16, Issue 4 https://doi.org/10.1109/TNN.2005.849836	journal	July 2005
Data Fusion and Multicue Data Matching by Diffusion Maps Lafon, S.; Keller, Y.; Coifman, R. R. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, Issue 11 https://doi.org/10.1109/TPAMI.2006.223	journal	November 2006
Clustering and Embedding Using Commute Times Qiu, Huaijun; Hancock, Edwin R. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, Issue 11 https://doi.org/10.1109/TPAMI.2007.1103	journal	November 2007
Fast approximated power iteration subspace tracking Badeau, R.; David, B.; Richard, G. IEEE Transactions on Signal Processing, Vol. 53, Issue 8 https://doi.org/10.1109/TSP.2005.850378	journal	August 2005
Accurate parameter estimation for star formation history in galaxies using SDSS spectra Richards, Joseph W.; Freeman, Peter E.; Lee, Ann B. Monthly Notices of the Royal Astronomical Society, Vol. 399, Issue 2 https://doi.org/10.1111/j.1365-2966.2009.15349.x	journal	October 2009
A Concise and Provably Informative Multi‐Scale Signature Based on Heat Diffusion Sun, Jian; Ovsjanikov, Maks; Guibas, Leonidas Computer Graphics Forum, Vol. 28, Issue 5 https://doi.org/10.1111/j.1467-8659.2009.01515.x	journal	July 2009
Spectral clustering based on the graph p -Laplacian Bühler, Thomas; Hein, Matthias Proceedings of the 26th Annual International Conference on Machine Learning https://doi.org/10.1145/1553374.1553385	conference	June 2009
On evolutionary spectral clustering Chi, Yun; Song, Xiaodan; Zhou, Dengyong ACM Transactions on Knowledge Discovery from Data, Vol. 3, Issue 4 https://doi.org/10.1145/1631162.1631165	journal	November 2009
Locally-scaled spectral clustering using empty region graphs Correa, Carlos D.; Lindstrom, Peter Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining https://doi.org/10.1145/2339530.2339736	conference	August 2012
Active spectral clustering via iterative uncertainty reduction Wauthier, Fabian L.; Jojic, Nebojsa; Jordan, Michael I. Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining https://doi.org/10.1145/2339530.2339737	conference	August 2012
Local anomaly descriptor Huang, Hao; Qin, Hong; Yoo, Shinjae Proceedings of the 21st ACM international conference on Information and knowledge management https://doi.org/10.1145/2396761.2396815	conference	October 2012
The complexity of the matrix eigenproblem Pan, Victor Y.; Chen, Zhao Q. Proceedings of the thirty-first annual ACM symposium on Theory of computing - STOC '99 https://doi.org/10.1145/301250.301389	conference	January 1999
OPTICS: ordering points to identify the clustering structure Ankerst, Mihael; Breunig, Markus M.; Kriegel, Hans-Peter Proceedings of the 1999 ACM SIGMOD international conference on Management of data - SIGMOD '99 https://doi.org/10.1145/304182.304187	conference	January 1999
LOF: identifying density-based local outliers Breunig, Markus M.; Kriegel, Hans-Peter; Ng, Raymond T. Proceedings of the 2000 ACM SIGMOD international conference on Management of data - SIGMOD '00 https://doi.org/10.1145/342009.335388	conference	January 2000
Discovery of climate indices using clustering Steinbach, Michael; Tan, Pang-Ning; Kumar, Vipin Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '03 https://doi.org/10.1145/956750.956801	conference	January 2003

Similar Records

Data depth based clustering analysis

Conference · Thu Dec 31 23:00:00 EST 2015 · OSTI ID:1438413

Robust and Simple ADMM Penalty Parameter Selection

Journal Article · Tue Jan 09 23:00:00 EST 2024 · IEEE Open Journal of Signal Processing (Online) · OSTI ID:2283368

Related Subjects

97 MATHEMATICS AND COMPUTING

Density-Aware Clustering Based on Aggregated Heat Kernel and Its Transformation

Citation Formats

References (36)

Similar Records

Related Subjects