Solving for multi-class using orthogonal coding matrices

TL;DR

This study evaluates orthogonal error correcting codes (ECCs) for multi-class classification, demonstrating their speed advantages and varying accuracy improvements depending on the classifier type and dataset, with notable benefits over random ECCs.

Contribution

It introduces and tests orthogonal ECCs with no zeros, showing their efficiency and accuracy benefits over random ECCs and traditional methods across multiple datasets and classifiers.

Findings

Orthogonal ECCs are more accurate than random ECCs.

Orthogonal ECCs are always faster than other multi-class methods with linear classifiers.

Accuracy gains are dataset and classifier dependent, with some cases favoring traditional methods.

Abstract

A common method of generalizing binary to multi-class classification is the error correcting code (ECC). ECCs may be optimized in a number of ways, for instance by making them orthogonal. Here we test two types of orthogonal ECCs on seven different datasets using three types of binary classifier and compare them with three other multi-class methods: 1 vs. 1, one-versus-the-rest and random ECCs. The first type of orthogonal ECC, in which the codes contain no zeros, admits a fast and simple method of solving for the probabilities. Orthogonal ECCs are always more accurate than random ECCs as predicted by recent literature. Improvments in uncertainty coefficient (U.C.) range between 0.4--17.5% (0.004--0.139, absolute), while improvements in Brier score between 0.7--10.7%. Unfortunately, orthogonal ECCs are rarely more accurate than 1 vs. 1. Disparities are worst when the methods are paired with logistic regression, with orthogonal ECCs never beating 1 vs. 1. When the methods are paired with SVM, the losses are less significant, peaking at 1.5%, relative, 0.011 absolute in uncertainty coefficient and 6.5% in Brier scores. Orthogonal ECCs are always the fastest of the five multi-class methods when paired with linear classifiers. When paired with a piecewise linear classifier, whose classification speed does not depend on the number of training samples, classifications using orthogonal ECCs were always more accurate than the other methods and also faster than 1 vs. 1. Losses against 1 vs. 1 here were higher, peaking at 1.9% (0.017, absolute), in U.C. and 39% in Brier score. Gains in speed ranged between 1.1% and over 100%. Whether the speed increase is worth the penalty in accuracy will depend on the application.