Single Class Universum-SVM

TL;DR

This paper introduces a novel Single Class Universum-SVM method that leverages additional domain-specific data samples from a different distribution to improve single-class learning performance.

Contribution

It extends Universum learning to single-class problems by incorporating a priori knowledge through Universum data, based on the connection between binary and single-class classification.

Findings

Improved single-class classification accuracy with Universum data

Demonstrated utility through empirical comparisons

Enhanced learning performance in domain-specific scenarios

Abstract

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.