Semi-supervised learning combining transductive support vector machine with active learning
- Boli Lu, Xibin Wang
- Corresponding Author
- Boli Lu
Available Online December 2015.
- https://doi.org/10.2991/icmmcce-15.2015.7How to use a DOI?
- Transductive support vector machine, Active learning, Graph-based learning
- In typical data mining applications, labeling the large amounts of data is difficult, expensive, and time consuming, if annotated manually.To avoid manual labeling, semi-supervised learninguses unlabeled data along withthe labeled data in the training process. Transductive support vector machine (TSVM) is one such semi-supervised, which has been found effective in enhancing the classification performance. However there are some deficiencies in TSVM, such as presetting number of the positive class samples, frequently exchange of class label, and its requirement for larger amount of unlabeled data. To tackle these deficiencies, in this paper, we propose a newsemi-supervised learning algorithm based on active learning (AL) combined with TSVM. The algorithm applies active learning to select the most informative instances based on the version space minimum-maximum division with human annotation for improve the classification performance.Simultaneously, in order to make full use of the distributioncharacteristics of unlabeled data, we addeda manifold regularization term to the objective function.Experiments performed on severalUCI datasetsdemonstrate that our proposedmethod achieves significant improvementoverother benchmark methods yet consuming less amount of human effort, which is very important while labeling data manually.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Boli Lu AU - Xibin Wang PY - 2015/12 DA - 2015/12 TI - Semi-supervised learning combining transductive support vector machine with active learning BT - 2015 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering PB - Atlantis Press UR - https://doi.org/10.2991/icmmcce-15.2015.7 DO - https://doi.org/10.2991/icmmcce-15.2015.7 ID - Lu2015/12 ER -