.png){kind=icon}
返回
Feature selection using Decomposed Mutual Information Maximization
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2022.09.101.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Feature selection has been recognized for long as an important preprocessing technique to reduce dimen-sionality and improve the performance of regression and classification tasks. The class of sequential for-ward feature selection methods based on Mutual Information (MI) is widely used in practice, mainly due to its computational efficiency and independence from the specific classifier. A recent work introduced a theoretical framework for this class of methods which explains the existing proposals as approximations to an optimal target objective function. Such framework made clear the advantages and drawbacks of each proposal. Methods accounting for the redundancy of candidate features using a maximization func-tion and considering the so-called complementary effect are among the best ones. However, they still penalize the complementarity, which is an important drawback. This paper proposes the Decomposed Mutual Information Maximization (DMIM) method, which keeps the good theoretical properties of the best methods proposed so far but overcomes the complementarity penalization by applying the maxi-mization separately to the inter-feature and class-relevant redundancies. DMIM was extensively evalu-ated and compared with other methods, both theoretically and using two synthetic scenarios and 20 publicly available real datasets applied to specific classifiers. Our results show that DMIM achieves a bet -ter classification performance than the remaining forward feature selection methods based on MI. (c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Keyword:
Mutual information
Feature selection
Classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Can high-order dependencies improve mutual information based feature selection?.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏Theoretical foundations of forward feature selection methods based on mutual informationNEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Multi-label feature selection based on label distribution and feature complementarity基于标签分布和特征互补的多标签特征选择
PREAI
分享收藏
查看更多内容