PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Causal Feature Selection
Isabelle Guyon, Andre Elisseeff and Constantin Aliferis
In: Computational Methods of Feature Selection Data Mining and Knowledge Discovery Series . (2007) Chapman and Hall/CRC , Boca Raton, London, New York , pp. 63-85. ISBN 1584888784

Abstract

This chapter reviews techniques for learning causal relationships from data, in application to the problem of feature selection. Most feature selection methods do not attempt to uncover causal relationships between feature and target and focus instead on making best predictions. We examine situations in which the knowledge of causal relationships benefits feature selection. Such benefits may include: explaining relevance in terms of causal mechanisms, distinguishing between actual features and experimental artifacts, predicting the consequences of actions performed by external agents, and making predictions in non-stationary environments. Conversely, we highlight the benefits that causal discovery may draw from recent developments in feature selection theory and algorithms.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Additional Information:The document provided is a larger Texreport on which the chapter is based.
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:4036
Deposited By:Isabelle Guyon
Deposited On:25 February 2008