TY - GEN
T1 - Efficient approximate solutions to mutual information based global feature selection
AU - Demakethepalli Venkateswara, Hemanth
AU - Lade, Prasanth
AU - Lin, Binbin
AU - Ye, Jieping
AU - Panchanathan, Sethuraman
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/1/5
Y1 - 2016/1/5
N2 - Mutual Information (MI) is often used for feature selection when developing classifier models. Estimating the MI for a subset of features is often intractable. We demonstrate, that under the assumptions of conditional independence, MI between a subset of features can be expressed as the Conditional Mutual Information (CMI) between pairs of features. But selecting features with the highest CMI turns out to be a hard combinatorial problem. In this work, we have applied two unique global methods, Truncated Power Method (TPower) and Low Rank Bilinear Approximation (LowRank), to solve the feature selection problem. These algorithms provide very good approximations to the NP-hard CMI based feature selection problem. We experimentally demonstrate the effectiveness of these procedures across multiple datasets and compare them with existing MI based global and iterative feature selection procedures.
AB - Mutual Information (MI) is often used for feature selection when developing classifier models. Estimating the MI for a subset of features is often intractable. We demonstrate, that under the assumptions of conditional independence, MI between a subset of features can be expressed as the Conditional Mutual Information (CMI) between pairs of features. But selecting features with the highest CMI turns out to be a hard combinatorial problem. In this work, we have applied two unique global methods, Truncated Power Method (TPower) and Low Rank Bilinear Approximation (LowRank), to solve the feature selection problem. These algorithms provide very good approximations to the NP-hard CMI based feature selection problem. We experimentally demonstrate the effectiveness of these procedures across multiple datasets and compare them with existing MI based global and iterative feature selection procedures.
UR - http://www.scopus.com/inward/record.url?scp=84963568328&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84963568328&partnerID=8YFLogxK
U2 - 10.1109/ICDM.2015.140
DO - 10.1109/ICDM.2015.140
M3 - Conference contribution
AN - SCOPUS:84963568328
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 1009
EP - 1014
BT - Proceedings - 15th IEEE International Conference on Data Mining, ICDM 2015
A2 - Aggarwal, Charu
A2 - Zhou, Zhi-Hua
A2 - Tuzhilin, Alexander
A2 - Xiong, Hui
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Data Mining, ICDM 2015
Y2 - 14 November 2015 through 17 November 2015
ER -