Classification from Positive and Biased Negative Data with Skewed Labeled Posterior Probability

TL;DR

This paper introduces a novel weakly supervised classification method that effectively learns from positive and biased negative data by correcting skewed posterior probabilities, demonstrated through experiments.

Contribution

It proposes a new approach to handle biased negative data in classification by correcting skewed posterior probabilities, improving learning accuracy.

Findings

Effective correction of skewed posterior probabilities.

Improved classification performance on biased datasets.

Validated through numerical and real data experiments.

Abstract

The binary classification problem has a situation where only biased data are observed in one of the classes. In this paper, we propose a new method to approach the positive and biased negative (PbN) classification problem, which is a weakly supervised learning method to learn a binary classifier from positive data and negative data with biased observations. We incorporate a method to correct the negative impact due to skewed confidence, which represents the posterior probability that the observed data are positive. This reduces the distortion of the posterior probability that the data are labeled, which is necessary for the empirical risk minimization of the PbN classification problem. We verified the effectiveness of the proposed method by numerical experiments and real data analysis.