Multi-Task Learning for HIV Therapy Screening
Abstract
We address the problem of learning classifiers for a large number of tasks. We derive a solution that produces resampling weights which match the pool of all examples to the target distribution of any given task. Our work is motivated by the problem of predicting the outcome of a therapy attempt for a patient who carries an HIV virus with a set of observed genetic properties. Such predictions need to be made for hundreds of possible combinations of drugs, some of which use similar biochemical mechanisms. Multi-task learning enables us to make predictions even for drug combinations with few or no training examples and substantially improves the overall prediction accuracy.
Cite
Text
Bickel et al. "Multi-Task Learning for HIV Therapy Screening." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390164Markdown
[Bickel et al. "Multi-Task Learning for HIV Therapy Screening." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/bickel2008icml-multi/) doi:10.1145/1390156.1390164BibTeX
@inproceedings{bickel2008icml-multi,
title = {{Multi-Task Learning for HIV Therapy Screening}},
author = {Bickel, Steffen and Bogojeska, Jasmina and Lengauer, Thomas and Scheffer, Tobias},
booktitle = {International Conference on Machine Learning},
year = {2008},
pages = {56-63},
doi = {10.1145/1390156.1390164},
url = {https://mlanthology.org/icml/2008/bickel2008icml-multi/}
}