Multitask Learning in Computational Biology

Christian Widmer, Gunnar Rätsch
Proceedings of ICML Workshop on Unsupervised and Transfer Learning, PMLR 27:207-216, 2012.

Abstract

Computational Biology provides a wide range of applications for Multitask Learning (MTL) methods. As the generation of labels often is very costly in the biomedical domain, combining data from different related problems or tasks is a promising strategy to reduce label cost. In this paper, we present two problems from sequence biology, where MTL was successfully applied. For this, we use regularization-based MTL methods, with a special focus on the case of a hierarchical relationship between tasks. Furthermore, we propose strategies to refine the measure of task relatedness, which is of central importance in MTL and finally give some practical guidelines, when MTL strategies are likely to pay off.

Cite this Paper


BibTeX
@InProceedings{pmlr-v27-widmer12a, title = {Multitask Learning in Computational Biology}, author = {Widmer, Christian and Rätsch, Gunnar}, booktitle = {Proceedings of ICML Workshop on Unsupervised and Transfer Learning}, pages = {207--216}, year = {2012}, editor = {Guyon, Isabelle and Dror, Gideon and Lemaire, Vincent and Taylor, Graham and Silver, Daniel}, volume = {27}, series = {Proceedings of Machine Learning Research}, address = {Bellevue, Washington, USA}, month = {02 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v27/widmer12a/widmer12a.pdf}, url = {https://proceedings.mlr.press/v27/widmer12a.html}, abstract = {Computational Biology provides a wide range of applications for Multitask Learning (MTL) methods. As the generation of labels often is very costly in the biomedical domain, combining data from different related problems or tasks is a promising strategy to reduce label cost. In this paper, we present two problems from sequence biology, where MTL was successfully applied. For this, we use regularization-based MTL methods, with a special focus on the case of a hierarchical relationship between tasks. Furthermore, we propose strategies to refine the measure of task relatedness, which is of central importance in MTL and finally give some practical guidelines, when MTL strategies are likely to pay off.} }
Endnote
%0 Conference Paper %T Multitask Learning in Computational Biology %A Christian Widmer %A Gunnar Rätsch %B Proceedings of ICML Workshop on Unsupervised and Transfer Learning %C Proceedings of Machine Learning Research %D 2012 %E Isabelle Guyon %E Gideon Dror %E Vincent Lemaire %E Graham Taylor %E Daniel Silver %F pmlr-v27-widmer12a %I PMLR %P 207--216 %U https://proceedings.mlr.press/v27/widmer12a.html %V 27 %X Computational Biology provides a wide range of applications for Multitask Learning (MTL) methods. As the generation of labels often is very costly in the biomedical domain, combining data from different related problems or tasks is a promising strategy to reduce label cost. In this paper, we present two problems from sequence biology, where MTL was successfully applied. For this, we use regularization-based MTL methods, with a special focus on the case of a hierarchical relationship between tasks. Furthermore, we propose strategies to refine the measure of task relatedness, which is of central importance in MTL and finally give some practical guidelines, when MTL strategies are likely to pay off.
RIS
TY - CPAPER TI - Multitask Learning in Computational Biology AU - Christian Widmer AU - Gunnar Rätsch BT - Proceedings of ICML Workshop on Unsupervised and Transfer Learning DA - 2012/06/27 ED - Isabelle Guyon ED - Gideon Dror ED - Vincent Lemaire ED - Graham Taylor ED - Daniel Silver ID - pmlr-v27-widmer12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 27 SP - 207 EP - 216 L1 - http://proceedings.mlr.press/v27/widmer12a/widmer12a.pdf UR - https://proceedings.mlr.press/v27/widmer12a.html AB - Computational Biology provides a wide range of applications for Multitask Learning (MTL) methods. As the generation of labels often is very costly in the biomedical domain, combining data from different related problems or tasks is a promising strategy to reduce label cost. In this paper, we present two problems from sequence biology, where MTL was successfully applied. For this, we use regularization-based MTL methods, with a special focus on the case of a hierarchical relationship between tasks. Furthermore, we propose strategies to refine the measure of task relatedness, which is of central importance in MTL and finally give some practical guidelines, when MTL strategies are likely to pay off. ER -
APA
Widmer, C. & Rätsch, G.. (2012). Multitask Learning in Computational Biology. Proceedings of ICML Workshop on Unsupervised and Transfer Learning, in Proceedings of Machine Learning Research 27:207-216 Available from https://proceedings.mlr.press/v27/widmer12a.html.

Related Material