Learnability with Partial Labels and Adaptive Nearest Neighbors

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Errandonea, Nicolas A., Mazuelas, Santiago, Lozano, Jose A., Dasgupta, Sanjoy
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918399764856832
author Errandonea, Nicolas A.
Mazuelas, Santiago
Lozano, Jose A.
Dasgupta, Sanjoy
author_facet Errandonea, Nicolas A.
Mazuelas, Santiago
Lozano, Jose A.
Dasgupta, Sanjoy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15781
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learnability with Partial Labels and Adaptive Nearest Neighbors
Errandonea, Nicolas A.
Mazuelas, Santiago
Lozano, Jose A.
Dasgupta, Sanjoy
Machine Learning
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.
title Learnability with Partial Labels and Adaptive Nearest Neighbors
topic Machine Learning
url https://arxiv.org/abs/2603.15781