CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise

TL;DR

This paper introduces a comprehensive framework for learning with class-conditional multi-label noise, addressing the challenge of multiple labels being corrupted simultaneously, and provides unbiased estimators with proven consistency.

Contribution

It formalizes the CCMN problem, develops unbiased estimators with error bounds, and applies these to partial multi-label learning, advancing robustness in multi-label noise scenarios.

Findings

The proposed estimators are unbiased and consistent with common multi-label loss functions.

Empirical results demonstrate the effectiveness of the method across multiple datasets.

The framework generalizes existing approaches to handle multi-label noise more effectively.

Abstract

Class-conditional noise commonly exists in machine learning tasks, where the class label is corrupted with a probability depending on its ground-truth. Many research efforts have been made to improve the model robustness against the class-conditional noise. However, they typically focus on the single label case by assuming that only one label is corrupted. In real applications, an instance is usually associated with multiple labels, which could be corrupted simultaneously with their respective conditional probabilities. In this paper, we formalize this problem as a general framework of learning with Class-Conditional Multi-label Noise (CCMN for short). We establish two unbiased estimators with error bounds for solving the CCMN problems, and further prove that they are consistent with commonly used multi-label loss functions. Finally, a new method for partial multi-label learning is implemented with unbiased estimator under the CCMN framework. Empirical studies on multiple datasets and various evaluation metrics validate the effectiveness of the proposed method.