Online Group Feature Selection from Feature Streams

Authors

  • Haiguang Li The University of Vermont
  • Xindong Wu The University of Vermont
  • Zhao Li TCL Research America
  • Wei Ding The University of Massachusetts Boston

DOI:

https://doi.org/10.1609/aaai.v27i1.8516

Abstract

Standard feature selection algorithms deal with given candidate feature sets at the individual feature level. When features exhibit certain group structures, it is beneficial to conduct feature selection in a grouped manner. For high-dimensional features, it could be far more preferable to online generate and process features one at a time rather than wait for generating all features before learning begins. In this paper, we discuss a new and interesting problem of online group feature selection from feature streams at both the group and individual feature levels simultaneously from a feature stream. Extensive experiments on both real-world and synthetic datasets demonstrate the superiority of the proposed algorithm.

 

Downloads

Published

2013-06-29

How to Cite

Li, H., Wu, X., Li, Z., & Ding, W. (2013). Online Group Feature Selection from Feature Streams. Proceedings of the AAAI Conference on Artificial Intelligence, 27(1), 1627-1628. https://doi.org/10.1609/aaai.v27i1.8516