Regularized Local Reconstruction for Clustering

Authors:
Jun Sun;Zhiyong Shen;Bai Su;Yidong Shen
Affiliations:
State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China 100190 and Chinese Academy of Sciences, Graduate University, Beijing, China 100049;State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China 100190 and Chinese Academy of Sciences, Graduate University, Beijing, China 100049;State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China 100190 and Chinese Academy of Sciences, Graduate University, Beijing, China 100049;State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China 100190
Venue:
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Year:
2009

Citing 11
Cited 0

Jacobi--Davidson Style QR and QZ Algorithms for the Reduction of Matrix Pencils

SIAM Journal on Scientific Computing
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cluster ensembles --- a knowledge reuse framework for combining multiple partitions

The Journal of Machine Learning Research
Think globally, fit locally: unsupervised learning of low dimensional manifolds

The Journal of Machine Learning Research
Multiclass Spectral Clustering

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Empirical and Theoretical Comparisons of Selected Criterion Functions for Document Clustering

Machine Learning
Convex Optimization

Convex Optimization
Learning Spectral Clustering, With Application To Speech Separation

The Journal of Machine Learning Research
Label Propagation through Linear Neighborhoods

IEEE Transactions on Knowledge and Data Engineering
Clustering Via Local Regression

ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
On Defining Partition Entropy by Inequalities

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motivated by the local reconstruction approach to discovering low dimensional structure in high dimensional data, we propose a novel clustering algorithm that effectively utilizes local reconstruction information. We obtain the local reconstruction weights by minimizing the reconstruction error between each data point and the reconstruction from its neighbors. An entropy regularization term is incorporated into the reconstruction objective function so that the smoothness of the reconstruction weights can be explicitly controlled. The reconstruction weights are then used to obtain the clustering result by employing spectral clustering techniques. Experimental results on a number of datasets demonstrate that our algorithm performs well relative to other approaches, which validate the effectiveness of our approach for clustering.