Single and Union Non-parallel Support Vector Machine Frameworks

TL;DR

This paper compares two frameworks for nonparallel support vector machines, introduces a new max-min distance-based NSVM for multiclass classification, and demonstrates its advantages through experiments.

Contribution

It introduces a novel max-min distance-based nonparallel SVM (NSVM) for multiclass classification, building on the second framework.

Findings

NSVM achieves larger margin hyperplanes.

Experimental results show NSVM's superior performance.

Comparison clarifies differences between frameworks.

Abstract

Considering the classification problem, we summarize the nonparallel support vector machines with the nonparallel hyperplanes to two types of frameworks. The first type constructs the hyperplanes separately. It solves a series of small optimization problems to obtain a series of hyperplanes, but is hard to measure the loss of each sample. The other type constructs all the hyperplanes simultaneously, and it solves one big optimization problem with the ascertained loss of each sample. We give the characteristics of each framework and compare them carefully. In addition, based on the second framework, we construct a max-min distance-based nonparallel support vector machine for multiclass classification problem, called NSVM. It constructs hyperplanes with large distance margin by solving an optimization problem. Experimental results on benchmark data sets show the advantages of our NSVM.