A Novel Semi-Supervised Learning Method Based on Broad Networks and Self-Paced Learning
International Journal of Cognitive Informatics and Natural Intelligence · 23.12.2025 · 20 (1) · 1-23
DOI: 10.4018/ijcini.397399 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Cognitive Informatics and Natural Intelligence, erschienen am 23.12.2025. Verfasst von Zhonglin Wan und 1 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
The acquisition of labeled data is costly in the era of big data. Semi-supervised learning (SSL) addresses this by integrating limited labeled data with large volumes of unlabeled data. However, SSL often presents limitations such as high computational complexity and noise sensitivity. This study introduced a semi-supervised learning method that integrates broad learning systems with a self-paced learning strategy. The method employed broad networks as the base model to reduce computational cost through efficient feature expansion, while self-paced learning dynamically assigned weights to samples based on their difficulty, enhancing robustness against noise. Experiments on multiple benchmark data sets showed that the proposed method demonstrated higher accuracy in data classification compared with existing SSL approaches, offering an effective solution to the challenges of efficiency and noise resistance.
Zitieren
APA
Wan, Z., & Li, H. (2025). A Novel Semi-Supervised Learning Method Based on Broad Networks and Self-Paced Learning. International Journal of Cognitive Informatics and Natural Intelligence, 20(1), 1-23. https://doi.org/10.4018/ijcini.397399
Vancouver
Wan Z, Li H. A Novel Semi-Supervised Learning Method Based on Broad Networks and Self-Paced Learning. International Journal of Cognitive Informatics and Natural Intelligence. 2025;20(1):1-23. doi:10.4018/ijcini.397399
BibTeX
@article{Wan2025,
author = {Wan, Zhonglin and Li, Hongyan},
title = {A Novel Semi-Supervised Learning Method Based on Broad Networks and Self-Paced Learning},
journal = {International Journal of Cognitive Informatics and Natural Intelligence},
year = {2025},
volume = {20},
number = {1},
pages = {1--23},
doi = {10.4018/ijcini.397399}
}
EUVIMED