# Semi-Supervised Learning of Classifiers from a Statistical Perspective: A Brief Review

arXiv: https://arxiv.org/abs/2104.04046 · HTML: https://mlsanity.com/paper/2104.04046/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 67 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [A Kernel Theory of Modern Data Augmentation](https://mlsanity.com/paper/1803.06084/) (2018)
- [Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference](https://mlsanity.com/paper/2010.09851/) (2020)
- [When can unlabeled data improve the learning rate?](https://mlsanity.com/paper/1905.11866/) (2019)
- [RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms](https://mlsanity.com/paper/1912.08766/) (2019)
- [Meta-Semi: A Meta-learning Approach for Semi-supervised Learning](https://mlsanity.com/paper/2007.02394/) (2020)
- [An Apparent Paradox: A Classifier Trained from a Partially Classified Sample May Have Smaller Expected Error Rate Than That If the Sample Were Completely Classified](https://mlsanity.com/paper/1910.09189/) (2019)
- [Fractionally-Supervised Classification](https://mlsanity.com/paper/1307.3598/) (2013)
- [On Fractionally-Supervised Classification: Weight Selection and Extension to the Multivariate t-Distribution](https://mlsanity.com/paper/1709.08258/) (2017)
- [Local Clustering with Mean Teacher for Semi-supervised Learning](https://mlsanity.com/paper/2004.09665/) (2020)
- [Harmless label noise and informative soft-labels in supervised classification](https://mlsanity.com/paper/2104.02872/) (2021)
- [Estimation of Classification Rules from Partially Classified Data](https://mlsanity.com/paper/2004.06237/) (2020)
- [A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data](https://mlsanity.com/paper/2011.08076/) (2020)

## Built on by (most cited first, 7 of 7)

- [Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost](https://mlsanity.com/paper/2403.07687/) (2024)
- [Analysis of Estimating the Bayes Rule for Gaussian Mixture Models with a Specified Missing-Data Mechanism](https://mlsanity.com/paper/2210.13785/) (2022)
- [Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training](https://mlsanity.com/paper/2408.04813/) (2024)
- [Informative missingness and its implications in semi-supervised learning](https://mlsanity.com/paper/2512.04392/) (2025)
- [Learning from Uncertainty-dependent Missing Labels for Semi-supervised Classification](https://mlsanity.com/paper/2608.23960/) (2026)
- [SSLfmm: An R Package for Semi-Supervised Learning with Mixed Missingness](https://mlsanity.com/paper/2512.03322/) (2025)
- [Semi-Supervised Classification with Informative Missing Labels in Weibull Mixture Models](https://mlsanity.com/paper/2609.00774/) (2026)

## Abstract (arXiv)

There has been increasing attention to semi-supervised learning (SSL) approaches in machine learning to forming a classifier in situations where the training data for a classifier consists of a limited number of classified observations but a much larger number of unclassified observations. This is because the procurement of classified data can be quite costly due to high acquisition costs and subsequent financial, time, and ethical issues that can arise in attempts to provide the true class labels for the unclassified data that have been acquired. We provide here a review of statistical SSL approaches to this problem, focussing on the recent result that a classifier formed from a partially classified sample can actually have smaller expected error rate than that if the sample were completely classified.