MFBLS: A Mixture-of-Experts-Based Fuzzy Broad Learning System for Tackling Imbalanced Datasets

作者：Jing Wang, Luyu Nie, Junwei Duan, Huimin Zhao, C. L. Philip Chen · 发表于：IEEE Transactions on Fuzzy Systems · 年份：2025 · DOI：10.1109/tfuzz.2025.3576155 · 被引用次数：5 · 研究领域：Machine Learning and ELM、Face and Expression Recognition、Text and Document Classification Technologies

Fuzzy Broad Learning System (Fuzzy BLS) constitutes an effective neural network architecture that has demonstrated remarkable efficacy across various real-world application domains. Nonetheless, Fuzzy BLS may result in suboptimal performance and face challenges in effectively addressing the issue of imbalanced classification. To tackle the challenge mentioned above, a novel Mixture-of-Expert-based Fuzzy Broad Learning System (MFBLS) is proposed. In MFBLS, a fuzzy system is integrated to deal with the fuzziness of input data. Concurrently, based on the advantages of the Mixture-of-expert framework, the feature weight of each expert system is dynamically adjusted via a gating network to enhance the importance of key features, thereby enhancing the overall capability of the model. Besides, several classical over-sampling techniques are employed to address sample imbalance in datasets to achieve a more balanced class distribution. Subsequently, the Extreme Gradient Boosting (XGBoost) algorithm is utilized on the oversampled dataset for feature selection, aiming to enhance the efficiency and the predictive precision of subsequent model training in MFBLS. Finally, through a comparative analysis of state-of-the-art machine learning methods, the superiority of MFBLS in handling imbalanced datasets is validated through a series of experimental evaluations on various imbalanced datasets.