Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection
Top Cited Papers
- 29 April 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 26 (9), 2138-2150
- https://doi.org/10.1109/tkde.2013.65
Abstract
Many pattern analysis and data mining problems have witnessed high-dimensional data represented by a large number of features, which are often redundant and noisy. Feature selection is one main technique for dimensionality reduction that involves identifying a subset of the most useful features. In this paper, a novel unsupervised feature selection algorithm, named clustering-guided sparse structural learning (CGSSL), is proposed by integrating cluster analysis and sparse structural analysis into a joint framework and experimentally evaluated. Nonnegative spectral clustering is developed to learn more accurate cluster labels of the input samples, which guide feature selection simultaneously. Meanwhile, the cluster labels are also predicted by exploiting the hidden structure shared by different features, which can uncover feature correlations to make the results more reliable. Row-wise sparse models are leveraged to make the proposed model suitable for feature selection. To optimize the proposed formulation, we propose an efficient iterative algorithm. Finally, extensive experiments are conducted on 12 diverse benchmarks, including face data, handwritten digit data, document data, and biomedical data. The encouraging experimental results in comparison with several representative algorithms and the theoretical analysis demonstrate the efficiency and effectiveness of the proposed algorithm for feature selection.Keywords
This publication has 27 references indexed in Scilit:
- Web Image Annotation Via Subspace-Sparsity Collaborated Feature SelectionIEEE Transactions on Multimedia, 2012
- On Similarity Preserving Feature SelectionIEEE Transactions on Knowledge and Data Engineering, 2011
- Unsupervised feature selection for multi-cluster dataPublished by Association for Computing Machinery (ACM) ,2010
- Discriminative Semi-Supervised Feature Selection Via Manifold RegularizationIEEE Transactions on Neural Networks, 2010
- A shared-subspace learning framework for multi-label classificationACM Transactions on Knowledge Discovery From Data, 2010
- Toward integrating feature selection algorithms for classification and clusteringIEEE Transactions on Knowledge and Data Engineering, 2005
- A Bayesian approach to joint feature selection and classifier designIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Accuracy and Stability of Numerical AlgorithmsPublished by Society for Industrial & Applied Mathematics (SIAM) ,2002
- Normalized cuts and image segmentationIeee Transactions On Pattern Analysis and Machine Intelligence, 2000
- Learning the parts of objects by non-negative matrix factorizationNature, 1999