• Cite Icon12
  • https://doi.org/10.4018/978-1-60566-010-3.ch272Copy DOI Icon

Semi-Supervised Learning

  • Jan 1, 2009
  • Tobias Scheffer
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

For many classification problems, unlabeled training data are inexpensive and readily available, whereas labeling training data imposes costs. Semi-supervised classification algorithms aim at utilizing information contained in unlabeled data in addition to the (few) labeled data. Semi-supervised (for an example, see Seeger, 2001) has a long tradition in statistics (Cooper & Freeman, 1970); much early work has focused on Bayesian discrimination of Gaussians. The Expectation Maximization (EM) algorithm (Dempster, Laird, & Rubin, 1977) is the most popular method for learning generative models from labeled and unlabeled data. Model-based, generative learning algorithms find model parameters (e.g., the parameters of a Gaussian mixture model) that best explain the available labeled and unlabeled data, and they derive the discriminating classification hypothesis from this model. In discriminative learning, unlabeled data is typically incorporated via the integration of some model assumption into the discriminative framework (Miller & Uyar, 1997; Titterington, Smith, & Makov, 1985). The Transductive Support Vector Machine (Vapnik, 1998; Joachims, 1999) uses unlabeled data to identify a hyperplane that has a large distance not only from the labeled data but also from all unlabeled data. This identification results in a bias toward placing the hyperplane in regions of low density p(x). Recently, studies have covered graph-based approaches that rely on the assumption that neighboring instances are more likely to belong to the same class than remote instances (Blum & Chawla, 2001). A distinct approach to utilizing unlabeled data has been proposed by de Sa (1994), Yarowsky (1995) and Blum and Mitchell (1998). When the available attributes can be split into independent and compatible subsets, then multi-view learning algorithms can be employed. Multi-view algorithms, such as co-training (Blum & Mitchell, 1998) and co-EM (Nigam & Ghani, 2000), learn two independent hypotheses, which bootstrap by providing each other with labels for the unlabeled data. An analysis of why training two independent hypotheses that provide each other with conjectured class labels for unlabeled data might be better than EM-like self-training has been provided by Dasgupta, Littman, and McAllester (2001) and has been simplified by Abney (2002). The disagreement rate of two independent hypotheses is an upper bound on the error rate of either hypothesis. Multi-view algorithms minimize the disagreement rate between the peer hypotheses (a situation that is most apparent for the algorithm of Collins & Singer, 1999) and thereby the error rate. Semi-supervised learning is related to active learning. Active learning algorithms are able to actively query the class labels of unlabeled data. By contrast, semi-supervised algorithms are bound to learn from the given data.

Similar Papers
  • Research Article
  • Citations20

SEMI-SUPERVISED SEQUENCE CLASSIFICATION WITH HMMs

  • Mar 01, 2005
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Shi Zhong
  • Research Article
  • Citations44

Deep Neural Backdoor in Semi-Supervised Learning: Threats and Countermeasures

  • Jan 01, 2021
  • IEEE Transactions on Information Forensics and Security
  • Zhicong Yan +4
  • Research Article
  • Citations114

Improving state-of-health estimation for lithium-ion batteries via unlabeled charging data

  • Oct 17, 2022
  • Energy Storage Materials
  • Chuanping Lin +2
  • Conference Article
  • Citations31

Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment

  • Jun 01, 2022
  • Yue Cao +4
  • Conference Article
  • Citations26

SILU: Strategy Involving Large-scale Unlabeled Logs for Improving Malware Detector

  • Jul 01, 2020
  • Taishi Nishiyama +3
  • Conference Article
  • Citations2

Benchmarking the semi-supervised naïve Bayes classifier

  • Jul 01, 2015
  • Awat A Saeed +2
  • Research Article
  • Citations37

Exploitation of unlabeled sequences in hidden Markov models

  • Dec 01, 2003
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • M Inoue +1
  • Book Chapter
  • Citations629

Semi-Supervised Learning

  • Jan 01, 2005
  • Tobias Scheffer
  • Research Article
  • Citations29

Semi-Supervised AUC Optimization Without Guessing Labels of Unlabeled Data

  • Apr 29, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zheng Xie +1
  • Research Article
  • Citations3

Active Labeling Aided Semi-Supervised Safety Assessment With Task-Related Unknown Scenarios

  • Dec 01, 2024
  • IEEE Transactions on Reliability
  • Chang Liu +4
  • Conference Article
  • Citations7

STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification

  • Oct 20, 2021
  • Hasib Zunair +3
  • Conference Article
  • Citations25

S3MKL

  • Oct 25, 2010
  • Shuhui Wang +3
  • Research Article

Two-way Markov random walk transductive learning algorithm

  • Mar 01, 2014
  • Journal of Central South University
  • Hong Li +3
  • Conference Article
  • Citations6

Learning Classifiers on Positive and Unlabeled Data with Policy Gradient

  • Nov 01, 2019
  • Tianyu Li +6
  • Conference Article

A safe semi-supervised kernel minimum squared error algorithm

  • Jul 01, 2015
  • Gan Haitao +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.