Loughborough University
Browse
An_adaptive_multi-class_imbalanced_classification_framework_based_on_ensemble_methods_and_deep_network.pdf (455.04 kB)

An adaptive multi-class imbalanced classification framework based on ensemble methods and deep network

Download (455.04 kB)
journal contribution
posted on 2023-03-14, 11:32 authored by Xuezheng Jiang, Junyi Wang, Qinggang MengQinggang Meng, Mohamad SaadaMohamad Saada, Haibin CaiHaibin Cai
Data imbalance is one of the most difficult problems in machine learning. The improved ensemble learning model is a promising solution to mitigate this challenge. In this paper, an improved multi-class imbalanced data classification framework is proposed by combining the Focal Loss with Boosting model (FL-Boosting). By addressing the confusion of the second-order derivation of Focal Loss in the traditional ensemble learning model, the proposed model achieves a more efficient and accurate classification of the imbalanced data. More specifically, a Highly Adaptive Focal Loss (HAFL) is proposed to ensure that the model maintains lasting attention to the minority samples, which could be combined with boosting model to build HAFL-Boosting to achieve better performance. The framework has the scalability to adapt to different situations according to typical ensemble learning algorithms such as LightGBM, XGBoost and CatBoost. In addition, to implement the application of the proposed framework on deep models, a two-stage classification method combining ConvNeXt with the improved boosting model is proposed, which could improve the recognition ability to high-dimensional imbalanced data. We evaluate the HAFL-Boosting and the two-stage class imbalance classification method by ablation experiments and benchmark experiments, which demonstrated that the proposed methods obviously improved the scores on several evaluation indexes. The comparative experiments with the latest classification models show that the proposed methods could achieve leading performance from multiple perspectives.

Funding

Research on Event-Triggered Synchronous Control of Input-Saturated Complex Networks in Network Environment

National Natural Science Foundation of China

Find out more...

Guangdong Basic and Applied Basic Research Foundation (2022A1515140126, 2023A1515011172)

Young and Middle-aged Science and Technology Innovation Talent of Shenyang (RC220485)

History

School

  • Science

Department

  • Computer Science

Published in

Neural Computing and Applications

Volume

35

Issue

15

Pages

11141-11159

Publisher

Springer

Version

  • AM (Accepted Manuscript)

Rights holder

The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature

Publisher statement

This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s00521-023-08290-w

Acceptance date

2023-01-06

Publication date

2023-02-20

Copyright date

2023

ISSN

0941-0643

eISSN

1433-3058

Language

  • en

Depositor

Dr Haibin Cai. Deposit date: 14 March 2023