Selecting informative universum sample for semi-supervised learning

Authors:
Shuo Chen;Changshui Zhang
Affiliations:
State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Automation, Tsinghua University, Beijing, China;State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Automation, Tsinghua University, Beijing, China
Venue:
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Year:
2009

Citing 4
Cited 3

Transductive Inference for Text Classification using Support Vector Machines

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Inference with the Universum

ICML '06 Proceedings of the 23rd international conference on Machine learning
Self-taught learning: transfer learning from unlabeled data

Proceedings of the 24th international conference on Machine learning
Self-taught clustering

Proceedings of the 25th international conference on Machine learning

Document clustering with universum

Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
Twin support vector machine with Universum data

Neural Networks
A nonparallel support vector machine for a classification problem with universum learning

Journal of Computational and Applied Mathematics

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Universum sample, which is defined as the sample that doesn't belong to any of the classes the learning task concerns, has been proved to be helpful in both supervised and semi-supervised settings. The former works treat the Universum samples equally. Our research found that not all the Universum samples are helpful, and we propose a method to pick the informative ones, i.e., in-between Universum samples. We also set up a new semi-supervised framework to incorporate the in-between Universum samples. Empirical experiments show that our method outperforms the former ones.