How Complex Is Your Classification Problem?: A Survey on Measuring Classification Complexity

Ana Carolina Lorena

doi:10.1145/3347711

Return

How Complex Is Your Classification Problem?: A Survey on Measuring Classification Complexity

2019-09-13

140

PRE

Ana Carolina Lorena *

Luís P. F. Garcia

Jens Lehmann

Marcílio C. P. de Souto

Tin Kam Ho

DOI：10.1145/3347711

Original

Original request for help

Save

Abstract

En 中文

Characteristics extracted from the training datasets of classification problems have proven to be effective predictors in a number of meta-analyses. Among them, measures of classification complexity can be used to estimate the difficulty in separating the data points into their expected classes. Descriptors of the spatial distribution of the data and estimates of the shape and size of the decision boundary are among the known measures for this characterization. This information can support the formulation of new data-driven preprocessing and pattern recognition techniques, which can in turn be focused on challenges highlighted by such characteristics of the problems. This article surveys and analyzes measures that can be extracted from the training datasets to characterize the complexity of the respective classification problems. Their use in recent literature is also reviewed and discussed, allowing to prospect opportunities for future work in the area. Finally, descriptions are given on an R package named Extended Complexity Library (ECoL) that implements a set of complexity measures and is made publicly available.

Keywords:

Supervised machine learning

classification

complexity measures

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.