Skip to search formSkip to main contentSkip to account menu

Semi-supervised learning

Known as: SSL, Semi supervised learning, Semisupervised learning 
Semi-supervised learning is a class of supervised learning tasks and techniques that also make use of unlabeled data for training – typically a small… 
Wikipedia (opens in a new tab)

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2016
Highly Cited
2016
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of… 
Highly Cited
2014
Highly Cited
2014
The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised… 
Highly Cited
2013
Highly Cited
2013
We propose the simple and efficient method of semi-supervised learning for deep neural networks. Basically, the proposed network… 
Highly Cited
2010
Highly Cited
2010
  • Xiaojin Zhu
  • Encyclopedia of Machine Learning
  • 2010
  • Corpus ID: 3869071
Semi-supervised learning uses both labeled and unlabeled data to perform an otherwise supervised learning or unsupervised… 
Highly Cited
2010
Highly Cited
2010
If we take an existing supervised NLP system, a simple and general way to improve accuracy is to use unsupervised word… 
Highly Cited
2009
Highly Cited
2009
Semi-supervised learning is a learning paradigm concerned with the study of how computers and natural systems such as humans… 
Highly Cited
2008
Highly Cited
2008
We show how nonlinear embedding algorithms popular for use with shallow semi-supervised learning techniques such as kernel… 
Review
2006
Review
2006
In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between supervised learning (in… 
Highly Cited
2004
Highly Cited
2004
We consider the semi-supervised learning problem, where a decision rule is to be learned from labeled and unlabeled data. In this… 
Highly Cited
2003
Highly Cited
2003
An approach to semi-supervised learning is proposed that is based on a Gaussian random field model. Labeled and unlabeled data…