Adaptive weighted broad learning system for imbalanced classification

Broad Learning System (BLS) perform well in classification tasks with good computational efficiency. However, its effectiveness decreases when faced with imbalanced data distribution. The traditional BLS cannot solve this problem effectively. In this paper, we introduce an adaptive weighted method for BLS, aiming to improve its classification performance on imbalanced data. This method can assign different weights according to the distribution characteristics of samples. There exists a closed-form solution to the problem and the transformation matrix can be solved efficiently by pseudo-inverse. Experimental results on several imbalanced datasets demonstrate that the proposed method surpasses standard BLS and many advanced imbalanced classification methods.