Saved in:
Bibliographic Details
Main Authors: Pham, Khiem, Herrmann, Charles, Zabih, Ramin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.00279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913673841213440
author Pham, Khiem
Herrmann, Charles
Zabih, Ramin
author_facet Pham, Khiem
Herrmann, Charles
Zabih, Ramin
contents A major challenge in Semi-Supervised Learning (SSL) is the limited information available about the class distribution in the unlabeled data. In many real-world applications this arises from the prevalence of long-tailed distributions, where the standard pseudo-label approach to SSL is biased towards the labeled class distribution and thus performs poorly on unlabeled data. Existing methods typically assume that the unlabeled class distribution is either known a priori, which is unrealistic in most situations, or estimate it on-the-fly using the pseudo-labels themselves. We propose to explicitly estimate the unlabeled class distribution, which is a finite-dimensional parameter, \emph{as an initial step}, using a doubly robust estimator with a strong theoretical guarantee; this estimate can then be integrated into existing methods to pseudo-label the unlabeled data during training more accurately. Experimental results demonstrate that incorporating our techniques into common pseudo-labeling approaches improves their performance.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving realistic semi-supervised learning with doubly robust estimation
Pham, Khiem
Herrmann, Charles
Zabih, Ramin
Machine Learning
A major challenge in Semi-Supervised Learning (SSL) is the limited information available about the class distribution in the unlabeled data. In many real-world applications this arises from the prevalence of long-tailed distributions, where the standard pseudo-label approach to SSL is biased towards the labeled class distribution and thus performs poorly on unlabeled data. Existing methods typically assume that the unlabeled class distribution is either known a priori, which is unrealistic in most situations, or estimate it on-the-fly using the pseudo-labels themselves. We propose to explicitly estimate the unlabeled class distribution, which is a finite-dimensional parameter, \emph{as an initial step}, using a doubly robust estimator with a strong theoretical guarantee; this estimate can then be integrated into existing methods to pseudo-label the unlabeled data during training more accurately. Experimental results demonstrate that incorporating our techniques into common pseudo-labeling approaches improves their performance.
title Improving realistic semi-supervised learning with doubly robust estimation
topic Machine Learning
url https://arxiv.org/abs/2502.00279