Learnability with Partial Labels and Adaptive Nearest Neighbors

TL;DR

This paper characterizes the conditions under which partial labels learning (PLL) is feasible and introduces an adaptive nearest-neighbors algorithm, PL A-$k$NN, that outperforms existing methods in general scenarios.

Contribution

The paper provides a mathematical characterization of feasible PLL settings and proposes a new adaptive nearest-neighbors algorithm with strong performance guarantees.

Findings

PL A-$k$NN outperforms state-of-the-art methods in general PLL scenarios.

Theoretical conditions for successful PLL are established.

Experimental results validate the effectiveness of the proposed method.

Abstract

Prior work on partial labels learning (PLL) has shown that learning is possible even when each instance is associated with a bag of labels, rather than a single accurate but costly label. However, the necessary conditions for learning with partial labels remain unclear, and existing PLL methods are effective only in specific scenarios. In this work, we mathematically characterize the settings in which PLL is feasible. In addition, we present PL A-$k$NN, an adaptive nearest-neighbors algorithm for PLL that is effective in general scenarios and enjoys strong performance guarantees. Experimental results corroborate that PL A-$k$NN can outperform state-of-the-art methods in general PLL scenarios.