Instance-Dependent Partial Label Learning

TL;DR

This paper introduces a novel instance-dependent partial label learning method that leverages latent label distributions to improve predictive accuracy, addressing the limitations of previous approaches that assume random incorrect labels.

Contribution

The paper proposes a new PLL approach that recovers latent label distributions using a variational inference framework, enhancing model training with instance-dependent label information.

Findings

The proposed method outperforms existing PLL approaches on benchmark datasets.

Latent label distributions improve the accuracy of label disambiguation.

Experimental results validate the effectiveness of the variational label enhancement technique.

Abstract

Partial label learning (PLL) is a typical weakly supervised learning problem, where each training example is associated with a set of candidate labels among which only one is true. Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels. However, this assumption is not realistic since the candidate labels are always instance-dependent. In this paper, we consider instance-dependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature. The incorrect label with a high degree is more likely to be annotated as the candidate label. Therefore, the latent label distribution is the essential labeling information in partially labeled examples and worth being leveraged for predictive model training. Motivated by this consideration, we propose a novel PLL method that recovers the label distribution as a label enhancement (LE) process and trains the predictive model iteratively in every epoch. Specifically, we assume the true posterior density of the latent label distribution takes on the variational approximate Dirichlet density parameterized by an inference model. Then the evidence lower bound is deduced for optimizing the inference model and the label distributions generated from the variational posterior are utilized for training the predictive model. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed method. Source code is available at https://github.com/palm-ml/valen.