Progressive Purification for Instance-Dependent Partial Label Learning

TL;DR

This paper introduces POP, a theoretically grounded method for instance-dependent partial label learning that progressively purifies candidate label sets to improve classifier accuracy, supported by theoretical guarantees and empirical validation.

Contribution

The paper proposes POP, a novel approach that progressively purifies candidate labels in instance-dependent PLL, with theoretical convergence guarantees and improved performance over existing methods.

Findings

POP enlarges the reliable model region rapidly.

POP approximates the Bayes optimal classifier under mild assumptions.

Experiments validate POP's effectiveness on benchmark and real-world datasets.

Abstract

Partial label learning (PLL) aims to train multiclass classifiers from the examples each annotated with a set of candidate labels where a fixed but unknown candidate label is correct. In the last few years, the instance-independent generation process of candidate labels has been extensively studied, on the basis of which many theoretical advances have been made in PLL. Nevertheless, the candidate labels are always instance-dependent in practice and there is no theoretical guarantee that the model trained on the instance-dependent PLL examples can converge to an ideal one. In this paper, a theoretically grounded and practically effective approach named POP, i.e. PrOgressive Purification for instance-dependent partial label learning, is proposed. Specifically, POP updates the learning model and purifies each candidate label set progressively in every epoch. Theoretically, we prove that POP enlarges the region appropriately fast where the model is reliable, and eventually approximates the Bayes optimal classifier with mild assumptions. Technically, POP is flexible with arbitrary PLL losses and could improve the performance of the previous PLL losses in the instance-dependent case. Experiments on the benchmark datasets and the real-world datasets validate the effectiveness of the proposed method.