Feature selection method reducing correlations among features by embedding domain knowledge

Yue Liu

doi:10.1016/j.actamat.2022.118195

2022-10-01

PRE

DOI：10.1016/j.actamat.2022.118195

原文链接

原文求助

摘要

En 中文

Selecting proper descriptors, also known as features, is one of the key problems in modeling for materials properties using machine learning models. Redundant features reduce accuracy of machine learning modeling, and results of purely data-driven feature selection methods are often inconsistent with materials domain knowledge. Herein, a feature selection method embedded with materials domain knowledge named NCOR-FS is proposed to select higher quality features. The method translates materials domain knowledge about highly correlated features into Non-Co-Occurrence Rules (NCORs), which allows to quantify the degree to which NCORs are violated by feature subsets and to design optimization process for FS method based on swarm intelligence algorithm. Experiments on seven datasets show that compared with multiple other FS methods commonly used in materials, NCOR-FS selects the feature subset with more appropriate number of highly correlated features, which improves the prediction accuracy and interpretability of the ML model. NCOR-FS can be applied to any materials systems, and the idea of embedding domain knowledge into data-driven algorithm is expected to facilitate constructing extensive machine learning models embedded with materials domain knowledge. (c) 2022 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Keyword:

Feature Selection

Domain Knowledge

Machine Learning

Materials Science

期刊

Acta Materialia

IF:

9.3

论文数:

2.0W

被引数:

12.9W

机构

shanghai university

学者数:

3.9W

论文数: 2.7W

被引数: 52

引用论文

PhIP-Seq Reveals Autoantibodies for Ubiquitously Expressed Antigens in Viral Myocarditis

Biology

IF0

2022-07-13

OAAI

Mahima T. Rasquinha; Ninaad Lasrado; Erika Petro-Turnquist; Eric Weaver; Thiagarajan Venkataraman; Daniel Anderson; Uri Laserson; H. Benjamin Larman; Jay Reddy

A highly efficient and informative method to identify ion transport networks in fast ion conductors 快速离子导体中识别离子传输网络的高效且信息丰富的方法

ACTA MATERIALIA

IF9.3

2021-01-01

PREAI

He, Bing; Mi, Penghui; Ye, Anjiang; Chi, Shuting; Jiao, Yao; Zhang, Liwen; Pu, Bowei; Zou, Zheyi; Zhang, Wenqing; Avdeev, Maxim; Adams, Stefan; Zhao, Jingtai; Shi, Siqi

Informatics-Aided Density Functional Theory Study on the Li Ion Transport of Tavorite-Type L1MTO4F (M3+ -T5+, Ni2+-T6+)

JOURNAL OF CHEMICAL INFORMATION AND MODELING

IF5.3

2015-06-03

PREAI

Jalem, Randy; Kimura, Mayumi; Nakayama, Masanobu; Kasuga, Toshihiro

ST2 Testing for Chronic Heart Failure Therapy Monitoring: The International ST2 Consensus Panel

The American Journal of Cardiology

IF0

2015-04-01

PREAI

James L. Januzzi; Domingo Pascual-Figal; Lori B. Daniels