Learnability with partial labels and adaptive nearest neighbors

Nicolás A. Errandonea, Santiago Mazuelas, Jose A. Lozano, Sanjoy Dasgupta

TL;DR: In this paper we characterize the scenarios in which partial labels learning is feasible and introduce PL A-kNN, an algorithm for partial labels that is effective in general scenarios.

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 scenarios 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

Submission Number: 1487