A survey on semi-supervised learning

Jesper E. van Engelen; Holger H. Hoos

doi:https://doi.org/10.1007/s10994-019-05855-6

A survey on semi-supervised learning

2019 · Machine Learning · 2,636 citations · 0 from inside this corpus

Abstract Semi-supervised learning is the branch of machine learning concerned with using labelled as well as unlabelled data to perform certain learning tasks. Conceptually situated between supervised and unsupervised learning, it permits harnessing the large amounts of unlabelled data available in many use cases in combination with typically smaller sets of labelled data. In recent years, research in this area has followed the general trends observed in machine learning, with much attention directed at neural network-based models and generative learning. The literature on the topic has also expanded in volume and scope, now encompassing a broad spectrum of theory, algorithms and applications. However, no recent surveys exist to collect and organize this knowledge, impeding the ability of researchers and engineers alike to utilize it. Filling this void, we present an up-to-date overview of semi-supervised learning methods, covering earlier work as well as more recent advances. We focus primarily on semi-supervised classification, where the large majority of semi-supervised learning research takes place. Our survey aims to provide researchers and practitioners new to the field as well as more advanced readers with a solid understanding of the main approaches and algorithms developed over the past two decades, with an emphasis on the most prominent and currently relevant work. Furthermore, we propose a new taxonomy of semi-supervised classification algorithms, which sheds light on the different conceptual and methodological approaches for incorporating unlabelled data into the training process. Lastly, we show how the fundamental assumptions underlying most semi-supervised learning algorithms are closely connected to each other, and how they relate to the well-known semi-supervised clustering assumption.

35 of 35 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

A survey on semi-supervised learning→Scikit-learn: Machine Learning in PythonLegacy edge — source detail unavailable
A survey on semi-supervised learning→XGBoostLegacy edge — source detail unavailable
A survey on semi-supervised learning→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
A survey on semi-supervised learning→Statistical Learning TheoryLegacy edge — source detail unavailable
A survey on semi-supervised learning→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
A survey on semi-supervised learning→Automatic differentiation in PyTorchLegacy edge — source detail unavailable
A survey on semi-supervised learning→Advances in Neural Information Processing Systems 14Legacy edge — source detail unavailable
A survey on semi-supervised learning→Deep LearningLegacy edge — source detail unavailable
A survey on semi-supervised learning→DeepWalkLegacy edge — source detail unavailable
A survey on semi-supervised learning→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
A survey on semi-supervised learning→Semi-Supervised Classification with Graph Convolutional NetworksLegacy edge — source detail unavailable
A survey on semi-supervised learning→Intriguing properties of neural networksLegacy edge — source detail unavailable
A survey on semi-supervised learning→Combining labeled and unlabeled data with co-trainingLegacy edge — source detail unavailable
A survey on semi-supervised learning→Natural Language Processing (almost) from ScratchLegacy edge — source detail unavailable
A survey on semi-supervised learning→Cluster Analysis for ApplicationsLegacy edge — source detail unavailable
A survey on semi-supervised learning→mixup: Beyond Empirical Risk MinimizationLegacy edge — source detail unavailable
A survey on semi-supervised learning→LINELegacy edge — source detail unavailable
A survey on semi-supervised learning→Semi-Supervised LearningLegacy edge — source detail unavailable
A survey on semi-supervised learning→Semi-Supervised Learning Literature SurveyLegacy edge — source detail unavailable
A survey on semi-supervised learning→Learning with Local and Global ConsistencyLegacy edge — source detail unavailable
A survey on semi-supervised learning→A sentimental educationLegacy edge — source detail unavailable
A survey on semi-supervised learning→Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…Legacy edge — source detail unavailable
A survey on semi-supervised learning→Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …Legacy edge — source detail unavailable
A survey on semi-supervised learning→Structural Deep Network EmbeddingLegacy edge — source detail unavailable
A survey on semi-supervised learning→Text Classification from Labeled and Unlabeled Documents using EMLegacy edge — source detail unavailable
A survey on semi-supervised learning→Spectral Networks and Locally Connected Networks on GraphsLegacy edge — source detail unavailable
A survey on semi-supervised learning→Transductive Inference for Text Classification using Support Vector MachinesLegacy edge — source detail unavailable
A survey on semi-supervised learning→Pattern recognition and machine learningLegacy edge — source detail unavailable
A survey on semi-supervised learning→Ensemble MethodsLegacy edge — source detail unavailable
A survey on semi-supervised learning→Unsupervised word sense disambiguation rivaling supervised methodsLegacy edge — source detail unavailable
A survey on semi-supervised learning→Why Does Unsupervised Pre-training Help Deep Learning?Legacy edge — source detail unavailable
A survey on semi-supervised learning→Ensemble Methods: Foundations and AlgorithmsLegacy edge — source detail unavailable
A survey on semi-supervised learning→The self-organizing mapLegacy edge — source detail unavailable
A survey on semi-supervised learning→Introduction to Semi-Supervised LearningLegacy edge — source detail unavailable
A survey on semi-supervised learning→Learning from Labeled and Unlabeled Data with Label PropagationLegacy edge — source detail unavailable
Semi-Supervised Learning→Learning from Labeled and Unlabeled Data with Label PropagationLegacy edge — source detail unavailable
Semi-Supervised Learning→Combining labeled and unlabeled data with co-trainingLegacy edge — source detail unavailable
Semi-Supervised Learning→Text Classification from Labeled and Unlabeled Documents using EMLegacy edge — source detail unavailable
Semi-Supervised Learning→Unsupervised word sense disambiguation rivaling supervised methodsLegacy edge — source detail unavailable
Semi-Supervised Learning→Transductive Inference for Text Classification using Support Vector MachinesLegacy edge — source detail unavailable
Semi-Supervised Learning→Statistical Learning TheoryLegacy edge — source detail unavailable
Semi-Supervised Learning→Learning with Local and Global ConsistencyLegacy edge — source detail unavailable
LINE→DeepWalkLegacy edge — source detail unavailable
Explaining and Harnessing Adversarial Examples→Intriguing properties of neural networksLegacy edge — source detail unavailable
Explaining and Harnessing Adversarial Examples→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Semi-Supervised LearningLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Combining labeled and unlabeled data with co-trainingLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Text Classification from Labeled and Unlabeled Documents using EMLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Unsupervised word sense disambiguation rivaling supervised methodsLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…Legacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Transductive Inference for Text Classification using Support Vector MachinesLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→A sentimental educationLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Semi-Supervised Learning Literature SurveyLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Statistical Learning TheoryLegacy edge — source detail unavailable
Introduction to Semi-Supervised Learning→Learning with Local and Global ConsistencyLegacy edge — source detail unavailable
Combining labeled and unlabeled data with co-training→Unsupervised word sense disambiguation rivaling supervised methodsLegacy edge — source detail unavailable
Dropout: a simple way to prevent neural networks from overfitting→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
Text Classification from Labeled and Unlabeled Documents using EM→Combining labeled and unlabeled data with co-trainingLegacy edge — source detail unavailable
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…→Semi-Supervised LearningLegacy edge — source detail unavailable
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…→Combining labeled and unlabeled data with co-trainingLegacy edge — source detail unavailable
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…→Text Classification from Labeled and Unlabeled Documents using EMLegacy edge — source detail unavailable
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…→Transductive Inference for Text Classification using Support Vector MachinesLegacy edge — source detail unavailable
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…→Statistical Learning TheoryLegacy edge — source detail unavailable
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…→Learning with Local and Global ConsistencyLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→Semi-Supervised LearningLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→Combining labeled and unlabeled data with co-trainingLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→Text Classification from Labeled and Unlabeled Documents using EMLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→Unsupervised word sense disambiguation rivaling supervised methodsLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→Transductive Inference for Text Classification using Support Vector MachinesLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→A sentimental educationLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→Statistical Learning TheoryLegacy edge — source detail unavailable
Semi-Supervised Learning Literature Survey→Learning with Local and Global ConsistencyLegacy edge — source detail unavailable
Why Does Unsupervised Pre-training Help Deep Learning?→Semi-Supervised LearningLegacy edge — source detail unavailable
Why Does Unsupervised Pre-training Help Deep Learning?→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
Learning with Local and Global Consistency→Statistical Learning TheoryLegacy edge — source detail unavailable
Natural Language Processing (almost) from Scratch→Transductive Inference for Text Classification using Support Vector MachinesLegacy edge — source detail unavailable
Natural Language Processing (almost) from Scratch→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
Structural Deep Network Embedding→LINELegacy edge — source detail unavailable
Structural Deep Network Embedding→A Fast Learning Algorithm for Deep Belief NetsLegacy edge — source detail unavailable
Structural Deep Network Embedding→DeepWalkLegacy edge — source detail unavailable
Semi-Supervised Classification with Graph Convolutional Networks→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Semi-Supervised Classification with Graph Convolutional Networks→Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…Legacy edge — source detail unavailable
Semi-Supervised Classification with Graph Convolutional Networks→Transductive Inference for Text Classification using Support Vector MachinesLegacy edge — source detail unavailable
mixup: Beyond Empirical Risk Minimization→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
mixup: Beyond Empirical Risk Minimization→Statistical Learning TheoryLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Learning from Labeled and Unlabeled Data with Label PropagationLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Intriguing properties of neural networksLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Pattern recognition and machine learningLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
Scikit-learn: Machine Learning in Python	2012	64,025
XGBoost	2016	52,304
Dropout: a simple way to prevent neural networks from overfitting	2014	34,236
Statistical Learning Theory	1999	26,957
A Fast Learning Algorithm for Deep Belief Nets	2006	16,540
Automatic differentiation in PyTorch	2017	11,099
Advances in Neural Information Processing Systems 14	2002	8,961
Deep Learning	2016	8,952
DeepWalk	2014	8,670
Explaining and Harnessing Adversarial Examples	2014	8,146
Semi-Supervised Classification with Graph Convolutional Networks	2016	8,058
Intriguing properties of neural networks	2013	5,739
Combining labeled and unlabeled data with co-training	1998	5,631
Natural Language Processing (almost) from Scratch	2011	5,174
Cluster Analysis for Applications	1973	5,152
mixup: Beyond Empirical Risk Minimization	2017	4,806
LINE	2015	4,752
Semi-Supervised Learning	2006	4,334
Semi-Supervised Learning Literature Survey	2005	3,879
Learning with Local and Global Consistency	2003	3,740
A sentimental education	2004	3,353
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Ex…	2006	3,266
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …	2018	2,873
Structural Deep Network Embedding	2016	2,843
Text Classification from Labeled and Unlabeled Documents using EM	2000	2,753
Spectral Networks and Locally Connected Networks on Graphs	2013	2,726
Transductive Inference for Text Classification using Support Vector Machines	1999	2,721
Pattern recognition and machine learning	2007	2,691
Ensemble Methods	2012	2,469
Unsupervised word sense disambiguation rivaling supervised methods	1995	2,436
Why Does Unsupervised Pre-training Help Deep Learning?	2010	2,114
Ensemble Methods: Foundations and Algorithms	2012	2,064
The self-organizing map	1998	1,982
Introduction to Semi-Supervised Learning	2009	1,812
Learning from Labeled and Unlabeled Data with Label Propagation	2002	1,570

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Domain Adaptation and Few-Shot Learning	Computer Science
Machine Learning and Data Classification	Computer Science
Text and Document Classification Technologies	Computer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports2 author record(s) attached.
supports264 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:49+00:00.

sha256 a2172c1bbe00c44b…