Ensemble constrained Laplacian score for efficient and robust semi-supervised feature selection

Khalid Benabdeslem 1 Haytham Elghazel 1 Mohammed Hindawi
1 DM2L - Data Mining and Machine Learning
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : In this paper, we propose an efficient and robust approach for semi-supervised feature selection, based on the constrainedLaplacian score. Themain drawback of this method is the choice of the scant supervision information, represented by pairwise constraints. In fact, constraints are proven to have some noise which may deteriorate learning performance. In this work, we try to override any negative effects of constraint set by the variation of their sources. This is achieved by an ensemble technique using both a resampling of data (bagging) and a random subspace strategy. Experiments on high-dimensional datasets are provided for validating the proposed approach and comparing it with other representative feature selection methods.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01233971
Contributor : Khalid Benabdeslem <>
Submitted on : Thursday, November 26, 2015 - 6:54:06 AM
Last modification on : Wednesday, November 20, 2019 - 3:18:15 AM

Identifiers

Citation

Khalid Benabdeslem, Haytham Elghazel, Mohammed Hindawi. Ensemble constrained Laplacian score for efficient and robust semi-supervised feature selection. Knowledge and Information Systems (KAIS), Springer, 2015, 45 (3), pp.1-25. ⟨10.1007/s10115-015-0901-0⟩. ⟨hal-01233971⟩

Share

Metrics

Record views

217