Introduction to Semi-Supervised Learning

By Xiaojin Zhu, Andrew B. Goldberg. 2009

2,315 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Representation & Self-Supervised Learning

Citations in the corpus

Data-Efficient Image Recognition with Contrastive Predictive Coding (2019, background): “The idea of semi-supervised learning is to leverage unlabeled data to improve task performance when few labeled examples are available [10, 70].”
Big Self-Supervised Models are Strong Semi-Supervised Learners (2020, methodology): “Aside from the representation learning paradigm, there is a large and diverse set of approaches for semi-supervised learning, we refer readers to [56–58] for surveys of classical approaches.”
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (2020, background): “In the semi-supervised setting [55, 56], an unsupervised loss is combined with a classification loss over a handful of labels to ground the training [19, 20, 57, 58, 59, 60, 61, 62].”
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020, neutral): “Broader introductions are provided in [60, 61, 6].”
Semi-Supervised Neural Architecture Search (2020, background): “In various scenarios with limited labeled training data, semi-supervised learning [40] is a popular approach to leverage unlabeled data to boost the training accuracy.”
Data Distillation: Towards Omni-Supervised Learning (2017, background): “There is a great volume of work on semi-supervised learning, and comprehensive surveys can be found in [49, 4, 50].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “in Adaptation for Visual Applications: A Comprehensive Survey 33 6.2 DA related to traditional ML methods Semi-supervised learning. DA can be seen as a particular case of the semi-supervised learning [248, 249], where, similarly to the majority of DA approaches, unlabeled data is exploited to remedy”
Data Classification: Algorithms and Applications (2014, background): “Surveys on semi-supervised methods may be found in [29, 96].”
Online Learning: A Comprehensive Survey (2018, background): “There are some surveys that introduce works in this field [289, 290].”
Contrastive Pessimistic Likelihood Estimation for Semi-Supervised Classification (2015, result): “Up to now, however, the literature has reported mixed results when it comes to such improvements; it is not always the case that semi-supervision leads to lower expected error rates or the like.”
Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2011, background): “Excellent, recent references for semi-supervised learning and active learning are [18, 19, 91, 104] which provide a nice structure to the vast amount of literature on these topics.”
P-N learning: Bootstrapping binary classifiers by structural constraints (2010, background): “exploiting both labeled and unlabeled data in classifier training [6, 24].”
A data-driven approach to cleaning large face datasets (2014, background): “We argue that for this particular application, we should prioritize achieving high recall (of outlier faces) over the other metrics, as we have plenty of data and can afford to mislabel some of them, if only to find more outliers.”
Semi-Supervised Learning (2014, neutral): “Many semi-supervised learning methods have been proposed, with different answers to these two questions [15, 7, 1, 10].”