Semi-supervised learning from a translation model between data distributions

Authors:
Henry Anaya-Sánchez;José Martínez-Sotoca;Adolfo Martínez-Usó
Affiliations:
Institute of New Imaging Technologies, Universitat Jaume I, Spain;Department of Languages and Computer Systems, Universitat Jaume I, Spain;Department of Languages and Computer Systems, Universitat Jaume I, Spain
Venue:
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Year:
2011

Citing 8
Cited 0

Information retrieval as statistical translation

Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Document language models, query models, and risk minimization for information retrieval

Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Probabilistic Discriminative Kernel Classifiers for Multi-class Problems

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Latent dirichlet allocation

The Journal of Machine Learning Research
Data spectroscopy: learning mixture models using eigenspaces of convolution operators

Proceedings of the 25th international conference on Machine learning
Semisupervised Multitask Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Semi-Supervised Learning

Introduction to Semi-Supervised Learning
Semi-supervised learning of facial attributes in video

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce a probabilistic classification model to address the task of semi-supervised learning. The major novelty of our proposal stems from measuring distributional relationships between the labeled and unlabeled data. This is achieved from a stochastic translation model between data distributions that is estimated from a mixture model. The proposed classifier is defined from the combination of both the translation model and a kernel logistic regression on labeled data. Experimental results obtained over synthetic and real-world data sets validate the usefulness of our proposal.