Balancing accuracy and diversity in ensemble learning using a two-phase artificial bee colony approach

In ensemble learning, it is necessary to build a balancing mechanism to balance the accuracy of individual learners with the diversity between individual learners to achieve excellent ensemble learning performance. In previous studies, diversity was regarded only as a regularization term, which does...

Full description

Saved in:
Bibliographic Details
Published in:Applied soft computing 2021-07, Vol.105, p.107212, Article 107212
Main Authors: Shiue, Yeou-Ren, You, Gui-Rong, Su, Chao-Ton, Chen, Hua
Format: Article
Language:English
Subjects:
Artificial bee colony algorithm
Ensemble diversity
Ensemble learning
Machine learning
Weighted ensemble
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In ensemble learning, it is necessary to build a balancing mechanism to balance the accuracy of individual learners with the diversity between individual learners to achieve excellent ensemble learning performance. In previous studies, diversity was regarded only as a regularization term, which does not sufficiently indicate that diversity should implicitly be treated as an accuracy factor. In this study, an ensemble learning approach based on balanced accuracy and diversity (ELBAD) that uses a two-phase artificial bee colony (ABC) algorithm is proposed to balance the accuracy and diversity of ensemble learners. In the first phase, the ABC algorithm is used to generate an ensemble classifier with appropriate diversity. In the second phase, the ABC algorithm is used to generate a weighted ensemble classifier. The ELBAD ensemble learning algorithm is significantly superior to other state-of-the-art popular ensemble learning algorithms, including AdaBoost, Bagging, Decorate, extremely randomized trees (ET), gradient boosting decision tree (GBDT), random forest (RF), and rotation forest (RoF) on 30 UCI datasets. In addition, this study proposes a systematic parameter tuning procedure for the ELBAD algorithm that reduces the time required to generate an ensemble classifier. •This study proposes the ELBAD approach to balance the accuracy of individual learners with their diversity.•A two-phase ABC algorithm can efficiently resolve the balancing mechanism.•The experimental results indicate the effectiveness of the proposed approach, which outperforms other state-of-the-art baselines.
ISSN:1568-4946
1872-9681
DOI:10.1016/j.asoc.2021.107212