Kernel-based semi-supervised learning for novelty detection

One-class Support Vector Machine (OCSVM) is a well-known method for novelty detection. However, OCSVM regards all negative data samples as a common symbol and thereby not being able to utilize the information carried by them. Furthermore, OCSVM requires a fully labeled data set and cannot work efficiently with data set with both labeled and unlabeled data samples which is very popular nowadays. In this paper, we first extend the model of OCSVM to enable efficiently using the negative data samples. We then propose two methods to integrate the semi-supervised learning paradigm to the extended model for novelty detection purpose.