Local-To-Global Semi-Supervised Feature selection - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Local-To-Global Semi-Supervised Feature selection

Mohammed Hindawi
Khalid Benabdeslem


Variable-weighting approaches are well-known in the context of embedded feature selection. Generally, feature selection is performed in a global way, when the algorithm selects a single cluster-independent subset of features (global feature selection). However, other approaches aim to select cluster-specific subsets of features (local feature selection). Global and local feature selection have different objectives, nevertheless, in this paper we propose a novel embedded approach which locally weighs the variables towards a global feature selection. The proposed approach is presented in the semi-supervised paradigm. Experiments on some known data sets are presented to validate our model and compare it with some representative methods.
No file

Dates and versions

hal-01339244 , version 1 (29-06-2016)



Mohammed Hindawi, Khalid Benabdeslem. Local-To-Global Semi-Supervised Feature selection. ACM International Conference on Information and Knowledge Management (CIKM 2013), Oct 2013, San Fransisco CA, United States. pp.2159-2168, ⟨10.1145/2505515.2505542⟩. ⟨hal-01339244⟩
95 View
0 Download



Gmail Facebook Twitter LinkedIn More