Ensemble Methods for Label Noise Detection Under the Noisy at Random Model
Kecia Gomes de Moura, Ricardo B. C. Prudêncio, George D. C. Cavalcanti · 2018
Label noise detection has been widely studied in Machine Learning due to its importance to improve training data quality. Effective noise detection has been achieved by adopting an ensemble of classifiers. In this approach, an instance is assigned as mislabeled if a high proportion of members in the pool misclassifies that instance. Previous authors have empirically evaluated this approach with interesting results, nevertheless, they mostly assumed that label noise is generated completely at random in a dataset. This is a gap in the literature since there are other types of label noise which are feasible in practice and can influence noise detection results. This paper investigates the performance of ensemble noise detection in a different noise model, the Noisy at Random (NAR) model, in which the probability of label noise depends on the instance class. In this setting, we also investigate the effect of class distribution on noise detection performance, since it changes the total noise level observed in a dataset under the NAR assumption. It is shown in a number of performed experiments that the choice for a noise generation model over another can lead to distinct results when taking in consideration aspects such as class imbalance and noise level ratio among different classes.