MLLGMar 8, 2020

Angle-Based Cost-Sensitive Multicategory Classification

arXiv:2003.03691v1
AI Analysis

This work addresses cost-sensitive classification for multicategory problems, which is important for real-world applications but remains challenging, though it is incremental in building on existing boosting methods.

The paper tackles multicategory classification with varying misclassification costs by proposing an angle-based cost-sensitive framework that avoids the sum-to-zero constraint, reducing computational complexity and leading to competitive performance in numerical experiments.

Many real-world classification problems come with costs which can vary for different types of misclassification. It is thus important to develop cost-sensitive classifiers which minimize the total misclassification cost. Although binary cost-sensitive classifiers have been well-studied, solving multicategory classification problems is still challenging. A popular approach to address this issue is to construct K classification functions for a K-class problem and remove the redundancy by imposing a sum-to-zero constraint. However, such method usually results in higher computational complexity and inefficient algorithms. In this paper, we propose a novel angle-based cost-sensitive classification framework for multicategory classification without the sum-to-zero constraint. Loss functions that included in the angle-based cost-sensitive classification framework are further justified to be Fisher consistent. To show the usefulness of the framework, two cost-sensitive multicategory boosting algorithms are derived as concrete instances. Numerical experiments demonstrate that proposed boosting algorithms yield competitive classification performances against other existing boosting approaches.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes