Abstract
Semisupervised classification (SSC) learns, from cheap unlabeled data and labeled data, to predict the labels of test instances. In order to make use of the information from unlabeled data, there should be an assumed relationship between the true class structure and the data distribution. One assumption is that data points clustered together are likely to have the same class label. In this paper, we propose a new algorithm, namely, cluster-based regularization (ClusterReg) for SSC, that takes the partition given by a clustering algorithm as a regularization term in the loss function of an SSC classifier. ClusterReg makes predictions according to the cluster structure together with limited labeled data. The experiments confirmed that ClusterReg has a good generalization ability for real-world problems. Its performance is excellent when data follows this cluster assumption. Even when these clusters have misleading overlaps, it still outperforms other state-of-the-art algorithms. © 2012 IEEE.
Original language | English |
---|---|
Article number | 6317193 |
Pages (from-to) | 1779-1792 |
Number of pages | 14 |
Journal | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 23 |
Issue number | 11 |
Early online date | 1 Oct 2012 |
DOIs | |
Publication status | Published - Nov 2012 |
Externally published | Yes |
Funding
This work was supported in part by The Capes Foundation, Ministry of Education of Brazil, Brazil, and the European Union Seventh Framework Programme under Grant 270428.; Funding text 2: Mr. Soares is a recipient of a scholarship from the Capes Foundation, Brazil, and the Brazilian Council for Scientific and Technological Development Scholarship.
Keywords
- Clustering
- machine learning
- regularization
- semisupervised learning