On Interacting Features in Subset Selection

View Sample PDF

Author(s): Zheng Zhao (Arizona State University, USA)
Copyright: 2009
Pages: 6
Source title: Encyclopedia of Data Warehousing and Mining, Second Edition
Source Author(s)/Editor(s): John Wang (Montclair State University, USA)
DOI: 10.4018/978-1-60566-010-3.ch167

Purchase

View On Interacting Features in Subset Selection on the publisher's website for pricing and purchasing information.

Abstract

The high dimensionality of data poses a challenge to learning tasks such as classification. In the presence of many irrelevant features, classification algorithms tend to overfit training data (Guyon & Elisseeff, 2003). Many features can be removed without performance deterioration, and feature selection is one effective means to remove irrelevant features (Liu & Yu, 2005). Feature selection, also known as variable selection, feature reduction, attribute selection or variable subset selection, is the technique of selecting a subset of relevant features for building robust learning models. Usually a feature is relevant due to two reasons: (1) it is strongly correlated with the target concept; or (2) it forms a feature subset with other features and the subset is strongly correlated with the target concept. Optimal feature selection requires an exponentially large search space (O(2n), where n is the number of features) (Almual-lim & Dietterich, 1994). Researchers often resort to various approximations to determine relevant features, and in many existing feature selection algorithms, feature relevance is determined by correlation between individual features and the class (Hall, 2000; Yu & Liu, 2003). However, a single feature can be considered irrelevant based on its correlation with the class; but when combined with other features, it can become very relevant. Unintentional removal of these features can result in the loss of useful information and thus may cause poor classification performance, which is studied as attribute interaction in (Jakulin & Bratko, 2003). Therefore, it is desirable to consider the effect of feature interaction in feature selection.

The IRMA Community

Research IRM

On Interacting Features in Subset Selection

Purchase

Abstract

Related Content

IRMA Sponsors