Metric-Based Methods for Adaptive Model Selection and Regularization
Machine Learning
Classifier Adaptation with Non-representative Training Data
DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
Toward a Computational Theory of Data Acquisition and Truthing
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
B-EM: a classifier incorporating bootstrap with EM approach for data mining
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Semisupervised learning from different information sources
Knowledge and Information Systems
Semi-supervised learning with an imperfect supervisor
Knowledge and Information Systems
ICML '05 Proceedings of the 22nd international conference on Machine learning
Improving the estimation of relevance models using large external corpora
SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
Incorporating large unlabeled data to enhance EM classification
Journal of Intelligent Information Systems
Privacy leakage in multi-relational databases: a semi-supervised learning perspective
The VLDB Journal — The International Journal on Very Large Data Bases
Semi-supervised model-based document clustering: A comparative study
Machine Learning
Automatic video annotation by semi-supervised learning with kernel density estimation
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Semi-supervised conditional random fields for improved sequence segmentation and labeling
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Analytical Results on Style-Constrained Bayesian Classification of Pattern Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Semi-supervised kernel density estimation for video annotation
Computer Vision and Image Understanding
Information theoretic regularization for semi-supervised boosting
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Humans perform semi-supervised classification too
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
A discriminative model for semi-supervised learning
Journal of the ACM (JACM)
Semisupervised multicategory classification with imperfect model
IEEE Transactions on Neural Networks
Using unsupervised analysis to constrain generalization bounds for support vector classifiers
IEEE Transactions on Neural Networks
Semi-supervised ranking for document retrieval
Computer Speech and Language
Learning aspect models with partially labeled data
Pattern Recognition Letters
Bayesian multiscale smoothing in supervised and semi-supervised kernel discriminant analysis
Computational Statistics & Data Analysis
Unsupervised Supervised Learning II: Margin-Based Classification Without Labels
The Journal of Machine Learning Research
A PAC-Style model for learning from labeled and unlabeled data
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Large-Scale inference of network-service disruption upon natural disasters
Sensor-KDD'08 Proceedings of the Second international conference on Knowledge Discovery from Sensor Data
A probabilistic approach for semi-supervised nearest neighbor classification
Pattern Recognition Letters
Semi-supervised learning with density-ratio estimation
Machine Learning
Manifold regularization and semi-supervised learning: some theoretical analyses
The Journal of Machine Learning Research
Unlabeling data can improve classification accuracy
Pattern Recognition Letters
| Hi-index | 0.00 |
We observe a training set Q composed of l labeled samples {(X1,θ1),...,(Xl, θl )} and u unlabeled samples {X1',...,Xu'}. The labels θi are independent random variables satisfying Pr{θi=1}=η, Pr{θi=2}=1-η. The labeled observations Xi are independently distributed with conditional density fθi(·) given θi. Let (X0 ,θ0) be a new sample, independently distributed as the samples in the training set. We observe X0 and we wish to infer the classification θ0. In this paper we first assume that the distributions f1(·) and f2(·) are given and that the mixing parameter is unknown. We show that the relative value of labeled and unlabeled samples in reducing the risk of optimal classifiers is the ratio of the Fisher informations they carry about the parameter η. We then assume that two densities g1(·) and g2(·) are given, but we do not know whether g1(·)=f1 (·) and g2(·)=f2(·) or if the opposite holds, nor do we know η. Thus the learning problem consists of both estimating the optimum partition of the observation space and assigning the classifications to the decision regions. Here, we show that labeled samples are necessary to construct a classification rule and that they are exponentially more valuable than unlabeled samples