Laplacian adaptive weighted discriminant analysis for semi-supervised multi-class classification
A multi-class discriminant analysis via adaptive weighted scheme (MDAAWS) has been proposed for supervised learning, which can deal with the issue that some classes may be vanished in the subspace. However, the acquisition of labeled data is expensive and time-consuming, while the unlabeled data is...
Saved in:
Published in | Neurocomputing (Amsterdam) Vol. 584; p. 127577 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
01.06.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | A multi-class discriminant analysis via adaptive weighted scheme (MDAAWS) has been proposed for supervised learning, which can deal with the issue that some classes may be vanished in the subspace. However, the acquisition of labeled data is expensive and time-consuming, while the unlabeled data is easy to obtained. To achieve a wide application, we propose a novel semi-supervised multi-class dimensionality reduction method based on MDAAWS, named Laplacian adaptive weighted discriminant analysis (LapAWDA), by applying manifold regularization to labeled and unlabeled data. This method inherits the merit of MDAAWS, assigning each pairwise class with an adaptive weight to avoid the issue of class vanishing. To enhance the robustness, we introduce the ℓ2,1 norm into LapAWDA to obtain a sparse discriminant projection matrix. Moreover, an alternative and iterative scheme is designed to find the solution of LapAWDA. Extensive experiments on several synthetic and real-world datasets demonstrate the excellent performance of LapAWDA. |
---|---|
ISSN: | 0925-2312 1872-8286 |
DOI: | 10.1016/j.neucom.2024.127577 |