TY - GEN
T1 - A Deep Reinforcement Learning Based Feature Selector
AU - Cheng, Yiran
AU - Komatsu, Kazuhiko
AU - Sato, Masayuki
AU - Kobayashi, Hiroaki
N1 - Publisher Copyright:
© 2021, Springer Nature Singapore Pte Ltd.
PY - 2021
Y1 - 2021
N2 - In the field of data mining and machine learning, it is a challenge for researchers and engineers to analyze and classify the high-dimensional data. In order to minimize the classification error, it is critical to identify and select the most characterizing features as well as remove the irrelevant features from the high-dimensional data. Feature selection algorithms provide effective processes to find a compact valuable feature subset from the set of all the candidate features. In past researches, most feature selection methods treat such a problem as a scoring problem, where each feature is evaluated individually and top-ranked features are selected. In this study, adding new features into the feature subset is considered as a Markov Decision Process, and the Feature Selection task is formalized as a reinforcement learning problem. This paper proposes a novel Deep Reinforcement Learning based Feature Selector (DRLFS) along with a dynamic randomness policy and two search protocols to tackle the exploration versus exploitation dilemma for a gradual approach to the optimum subset. The experimental results on various benchmark datasets prove the promising feature selection ability of the proposal of this paper.
AB - In the field of data mining and machine learning, it is a challenge for researchers and engineers to analyze and classify the high-dimensional data. In order to minimize the classification error, it is critical to identify and select the most characterizing features as well as remove the irrelevant features from the high-dimensional data. Feature selection algorithms provide effective processes to find a compact valuable feature subset from the set of all the candidate features. In past researches, most feature selection methods treat such a problem as a scoring problem, where each feature is evaluated individually and top-ranked features are selected. In this study, adding new features into the feature subset is considered as a Markov Decision Process, and the Feature Selection task is formalized as a reinforcement learning problem. This paper proposes a novel Deep Reinforcement Learning based Feature Selector (DRLFS) along with a dynamic randomness policy and two search protocols to tackle the exploration versus exploitation dilemma for a gradual approach to the optimum subset. The experimental results on various benchmark datasets prove the promising feature selection ability of the proposal of this paper.
KW - AutoML
KW - Data mining
KW - Feature selection
KW - High-dimensional data
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85102494710&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102494710&partnerID=8YFLogxK
U2 - 10.1007/978-981-16-0010-4_33
DO - 10.1007/978-981-16-0010-4_33
M3 - Conference contribution
AN - SCOPUS:85102494710
SN - 9789811600098
T3 - Communications in Computer and Information Science
SP - 378
EP - 389
BT - 11th International Symposium, PAAP 2020, Proceedings
A2 - Ning, Li
A2 - Chau, Vincent
A2 - Lau, Francis
PB - Springer Science and Business Media Deutschland GmbH
T2 - 11th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2020
Y2 - 28 December 2020 through 30 December 2020
ER -