Learning from Noisy Label Distributions
This addresses a novel machine learning problem for scenarios with group-level noisy data, but it appears incremental as it builds on existing probabilistic and variational methods.
The paper tackles the problem of learning a classifier from noisy label distributions, where instances are grouped and only distorted group-level label distributions are observed, and it shows that the proposed model outperforms existing methods in estimating true labels.
In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector belongs to at least one group. Then, instead of the true label of each instance, we observe the label distribution of the instances associated with a group, where the label distribution is distorted by an unknown noise. Our goals are to (1) estimate the true label of each instance, and (2) learn a classifier that predicts the true label of a new instance. We propose a probabilistic model that considers true label distributions of groups and parameters that represent the noise as hidden variables. The model can be learned based on a variational Bayesian method. In numerical experiments, we show that the proposed model outperforms existing methods in terms of the estimation of the true labels of instances.