Robust two-stage instance-level cost-sensitive learning method for class imbalance problem

doi:10.1016/j.knosys.2024.112143

Robust two-stage instance-level cost-sensitive learning method for class imbalance problem

2024-09-01

0

PRE

AI

DOI：10.1016/j.knosys.2024.112143

Original

Original request for help

Save

Abstract

En 中文

The class imbalance problem is a pervasive challenge in various applications, prompting researchers to design specialized loss functions for instance-level cost-sensitive learning models. However, the performance deteriorates when datasets are contaminated by label noise, especially in scenarios with uneven noise distribution. Additionally, specific hard-to-classify samples can further impede performance. Addressing these issues establishing a robust instance-level cost-sensitive learning framework remains a formidable challenge. this paper, we propose a robust Two-Stage instance-level cost-sensitive learning method with the Bounded Quadratic Type Squared Error (BQTSE) loss function, termed TSBQT. The asymmetric and bounded nature the BQTSE loss function not only allows for distinct cost assignments to majority and minority instances, also enhances the robustness to uneven noise. Moreover, our two-stage learning strategy prioritizes hard classify instances by considering their classification difficulty. We solve TSBQT using the alternating direction method of multipliers and gradient descent algorithm. The generalization capability of TSBQT is analyzed the Rademacher complexity theory. Extensive experiments validate the effectiveness of TSBQT.

Keywords:

Class imbalance problem

Cost-sensitive learning

Two-stage learning strategy

BQTSE loss function

Label noise

Robust two-stage instance-level cost-sensitive learning method for class imbalance problem

Abstract

Journal

Organization