An Algorithm for Transfer Learning in a Heterogeneous Environment
Abstract
We consider the problem of learning in an environment of classification tasks. Tasks sampled from the environment are used to improve classification performance on future tasks. We consider situations in which the tasks can be divided into groups. Tasks within each group are related by sharing a low dimensional representation, which differs across the groups. We present an algorithm which divides the sampled tasks into groups and computes a common representation for each group. We report experiments on a synthetic and two image data sets, which show the advantage of the approach over single-task learning and a previous transfer learning method.
Cite
Text
Argyriou et al. "An Algorithm for Transfer Learning in a Heterogeneous Environment." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2008. doi:10.1007/978-3-540-87479-9_23Markdown
[Argyriou et al. "An Algorithm for Transfer Learning in a Heterogeneous Environment." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2008.](https://mlanthology.org/ecmlpkdd/2008/argyriou2008ecmlpkdd-algorithm/) doi:10.1007/978-3-540-87479-9_23BibTeX
@inproceedings{argyriou2008ecmlpkdd-algorithm,
title = {{An Algorithm for Transfer Learning in a Heterogeneous Environment}},
author = {Argyriou, Andreas and Maurer, Andreas and Pontil, Massimiliano},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2008},
pages = {71-85},
doi = {10.1007/978-3-540-87479-9_23},
url = {https://mlanthology.org/ecmlpkdd/2008/argyriou2008ecmlpkdd-algorithm/}
}