Learning Causal Transition Matrix for Instance-dependent Label Noise

TL;DR

This paper introduces a causal approach to learn an instance-dependent transition matrix for noisy labels, improving label noise modeling by considering latent variables affecting label generation, and provides a theoretical guarantee for its approximation.

Contribution

It proposes a novel causal graph framework to model instance-dependent label noise and introduces a training method that better infers clean labels under complex noise scenarios.

Findings

The causal transition matrix approximates the true transition matrix with theoretical guarantees.

The proposed method improves label noise modeling in complex real-world scenarios.

Experimental results demonstrate enhanced label correction accuracy.

Abstract

Noisy labels are both inevitable and problematic in machine learning methods, as they negatively impact models' generalization ability by causing overfitting. In the context of learning with noise, the transition matrix plays a crucial role in the design of statistically consistent algorithms. However, the transition matrix is often considered unidentifiable. One strand of methods typically addresses this problem by assuming that the transition matrix is instance-independent; that is, the probability of mislabeling a particular instance is not influenced by its characteristics or attributes. This assumption is clearly invalid in complex real-world scenarios. To better understand the transition relationship and relax this assumption, we propose to study the data generation process of noisy labels from a causal perspective. We discover that an unobservable latent variable can affect either the instance itself, the label annotation procedure, or both, which complicates the identification of the transition matrix. To address various scenarios, we have unified these observations within a new causal graph. In this graph, the input instance is divided into a noise-resistant component and a noise-sensitive component based on whether they are affected by the latent variable. These two components contribute to identifying the ``causal transition matrix'', which approximates the true transition matrix with theoretical guarantee. In line with this, we have designed a novel training framework that explicitly models this causal relationship and, as a result, achieves a more accurate model for inferring the clean label.