Semi-Supervised Learning of Mixture Models

Semi-Supervised Learning of Mixture Models (2003)

Cached

Download Links

[www-connex.lip6.fr]
[www-poleia.lip6.fr]

Other Repositories/Bibliography

CiteULike
DBLP

by Fabio Gagliardi Cozman , Ira Cohen , Marcelo Cesar Cirelo , Escola Politécnica

Venue:	ICML-03, 20th International Conference on Machine Learning
Citations:	32 - 4 self

BibTeX

@INPROCEEDINGS{Cozman03semi-supervisedlearning,
    author = {Fabio Gagliardi Cozman and Ira Cohen and Marcelo Cesar Cirelo and Escola Politécnica},
    title = {Semi-Supervised Learning of Mixture Models},
    booktitle = {ICML-03, 20th International Conference on Machine Learning},
    year = {2003},
    pages = {99--106}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

This paper analyzes the performance of semisupervised learning of mixture models. We show that unlabeled data can lead to an increase in classification error even in situations where additional labeled data would decrease classification error. We present a mathematical analysis of this "degradation" phenomenon and show that it is due to the fact that bias may be adversely affected by unlabeled data. We discuss the impact of these theoretical results to practical situations.

Citations

801	A probabilistic theory of pattern recognition - Devroye, Györfi, et al. - 1996
633	T (2000) Text classification from labeled and unlabeled documents using EM - Nigam, McCallum, et al.
451	Bayesian Network Classifiers - Friedman, Geiger, et al. - 1997
376	K: Mixture Models: Inference and Applications to Clustering - McLachlan, Basford - 1988
359	Unsupervised models for named entity classification - Collins, Singer - 1999
323	PJ: The behaviour of maximum likelihood estimates under non-standard conditions - Huber
286	Discriminant Analysis and Statistical Pattern Recognition - McLachlan - 2004
279	Maximum likelihood estimate of misspecified models - White - 1982
198	Employing EM and pool-based active learning for text classification - McCallum, Nigam - 1998
95	Maximum entropy discrimination - Jaakkola, Meila, et al. - 1999
94	Enhancing Supervised Learning with Unlabelled Data - Goldman, Zhou - 2000
92	MI: Learning with mixtures of trees - Meila, Jordan
82	The relative value of labeled and unlabeled samples in pattern recognition with an unknown mixing parameter - Castelli, Cover - 1996
82	A mixture of experts classifier with learning based on both labelled and unlabelled data - Miller, Uyar - 1997
72	Effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon - Shahshahani, Landgrebe - 1994
72	A probability analysis on the value of unlabeled data for classification problems - Zhang, Oles - 2000
59	On the exponential value of labeled samples - Castelli, Cover - 1995
41	Using unlabeled data to improve text classification - Nigam - 2001
35	Probabilistic modeling for face orientation discrimination: learning from labeled and unlabeled data - Baluja - 1998
33	Learning from a mixture of labeled and unlabeled examples with parametric side information - Ratsaby, Venkatesh - 1995
32	Limiting behavior of posterior distributions when the model is incorrect - Berk - 1966
27	Unlabeled data can degrade classification performance of generative classifiers - Cozman, Cohen - 2002
26	Learning with labeled and unlabeled data (Technical Report - Seeger - 2001
25	Normal discrimination with unclassified observations - O’Neill - 1978
22	Learning bayesian network classifiers for facial expression recognition using both labeled and unlabeled data - Cohen, Sebe, et al. - 2003
19	Combining labeled and unlabeled data for text classification with a large number of categories - Ghani
18	Continuations methods for mixing heterogeneous sources - Corduneanu, Jaakkola - 2002
16	The efficiency of a linear discriminant function based on unclassified initial samples - Ganesalingam, McLachlan - 1978
15	Positive and unlabeled examples help learning - DeComité, Denis, et al. - 1999
12	Semi-supervised learning using prior probabilities and EM - Bruce - 2001
10	Classification of multi-spectral data by joint supervised-unsupervised learning - Shahshahani, Landgrebe - 1994
9	On the asymptotic improvement in the outcome of supervised learning provided by additional nonsupervised learning - Cooper, Freeman - 1970
7	Robustness in Statistical Pattern Recognition - Kharin - 1996
4	The effect of modeling errors in semi-supervised learning of mixture models: How unlabeled data can degrade performance of generative classifiers.” http://www.poli.usp.br/p/fabio.cozman/ Publications/lul.ps.gz - Cozman, Cohen - 2003
4	A Comparison of Iterative Maximum Likelihood Estimates of the Parameters of a Mixture of Two Normal Distributions Under Three Different Types of Sample - Jr - 1973