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.

DOI: 10.1007/978-3-540-87479-9_23

Extracted Key Phrases

11 Figures and Tables

Statistics

0510200920102011201220132014201520162017
Citations per Year

55 Citations

Semantic Scholar estimates that this publication has 55 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Argyriou2008AnAF, title={An Algorithm for Transfer Learning in a Heterogeneous Environment}, author={Andreas Argyriou and Andreas Maurer and Massimiliano Pontil}, booktitle={ECML/PKDD}, year={2008} }