Single Class Universum-SVM
This work addresses single-class learning problems for applications where only positive data is available, but it appears incremental as it builds on existing Universum and SVM frameworks.
The paper tackles the problem of single-class learning by extending Universum learning to incorporate a priori knowledge via additional data samples from the same domain but different distribution, resulting in a proposed Single Class Universum-SVM method with empirical comparisons to illustrate its utility.
This paper extends the idea of Universum learning [1, 2] to single-class learning problems. We propose Single Class Universum-SVM setting that incorporates a priori knowledge (in the form of additional data samples) into the single class estimation problem. These additional data samples or Universum belong to the same application domain as (positive) data samples from a single class (of interest), but they follow a different distribution. Proposed methodology for single class U-SVM is based on the known connection between binary classification and single class learning formulations [3]. Several empirical comparisons are presented to illustrate the utility of the proposed approach.