File(s) under permanent embargo
Exploiting feature relationships towards stable feature selection
conference contribution
posted on 2015-01-01, 00:00 authored by Iman Kamkar, S Gupta, Quoc-Dinh Phung, Svetha VenkateshSvetha VenkateshFeature selection is an important step in building predictive models for most real-world problems. One of the popular methods in feature selection is Lasso. However, it shows instability in selecting features when dealing with correlated features. In this work, we propose a new method that aims to increase the stability of Lasso by encouraging similarities between features based on their relatedness, which is captured via a feature covariance matrix. Besides modeling positive feature correlations, our method can also identify negative correlations between features. We propose a convex formulation for our model along with an alternating optimization algorithm that can learn the weights of the features as well as the relationship between them. Using both synthetic and real-world data, we show that the proposed method is more stable than Lasso and many state-of-the-art shrinkage and feature selection methods. Also, its predictive performance is comparable to other methods.
History
Event
Data Science and Advanced Analytics. Conference (2015 : Paris, France)Pagination
1 - 10Publisher
IEEELocation
Paris, FrancePlace of publication
Piscataway, N.J.Publisher DOI
Start date
2015-10-19End date
2015-10-21ISBN-13
9781467382724Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2015, IEEEEditor/Contributor(s)
E Gaussier, L Cao, P Gallinari, J Kwok, G Pasi, O ZaianeTitle of proceedings
DSAA 2015: IEEE International Conference on Data Science and Advanced AnalyticsUsage metrics
Categories
No categories selectedKeywords
stabilityLassocorrelated featurespredictionnonparametric discoveryOnline communitiesmental Healthmoods and emotiontopicssocial mediaScience & TechnologyTechnologyComputer Science, Information SystemsComputer Science, Interdisciplinary ApplicationsComputer ScienceDEPRESSIONAUTISMVARIABLE SELECTIONMODEL SELECTIONREGRESSIONPREDICTORMORTALITYSURVIVALCANCER
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC