Principal component analysis (PCA) has been extensively applied in data mining, pattern recognition and information retrieval for unsupervised dimensionality reduction. When labels of data are available, e.g.,~in a classification or regression task, PCA is however not able to use this information. The problem is more interesting if only part of the input data are labeled, i.e.,~in a semi-supervised setting. In this paper we propose a supervised PCA model called SPPCA and a semi-supervised PCA model called S$^2$PPCA, both of which are extensions of a probabilistic PCA model. The proposed models are able to incorporate the label information into the projection phase, and can naturally handle multiple outputs (i.e.,~in multi-task learning problems). We derive an efficient EM learning algorithm for both models, and also provide theoretical justifications of the model behaviors. SPPCA and S$^2$PPCA are compared with other supervised projection methods on various learning tasks, and show not only promising performance but also good scalability.
| Author(s): | Yu, S. and Yu, K. and Tresp, V. and Kriegel, H-P. and Wu, M. |
| Book Title: | KDD 2006 |
| Journal: | Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2006) |
| Pages: | 464-473 |
| Year: | 2006 |
| Month: | August |
| Day: | 0 |
| Editors: | Ungar, L. |
| Publisher: | ACM Press |
| Bibtex Type: | Conference Paper (inproceedings) |
| Address: | New York, NY, USA |
| DOI: | 10.1145/1150402.1150454 |
| Event Name: | 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |
| Event Place: | Philadelphia, PA, USA |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
| Links: | |
BibTex
@inproceedings{4069,
title = {Supervised Probabilistic Principal Component Analysis},
journal = {Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2006)},
booktitle = {KDD 2006},
abstract = {Principal component analysis (PCA) has been extensively applied in
data mining, pattern recognition and information retrieval for
unsupervised dimensionality reduction. When labels of data are
available, e.g.,~in a classification or regression task, PCA is however not able to use this information. The problem is more interesting if only part of the input data are labeled, i.e.,~in a
semi-supervised setting. In this paper we propose a supervised PCA
model called SPPCA and a semi-supervised PCA model called S$^2$PPCA, both of which are extensions of a probabilistic PCA model. The proposed models are able to incorporate the label information into
the projection phase, and can naturally handle multiple outputs
(i.e.,~in multi-task learning problems). We derive an efficient EM
learning algorithm for both models, and also provide theoretical
justifications of the model behaviors. SPPCA and S$^2$PPCA are
compared with other supervised projection methods on various
learning tasks, and show not only promising performance but also
good scalability.},
pages = {464-473},
editors = {Ungar, L. },
publisher = {ACM Press},
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
address = {New York, NY, USA},
month = aug,
year = {2006},
slug = {4069},
author = {Yu, S. and Yu, K. and Tresp, V. and Kriegel, H-P. and Wu, M.},
month_numeric = {8}
}