ICML 2011 workshop on unsupervised
and transfer learning
Transfer Learning in Computational Biology
Christian Widmer
and Gunnar Raetsch
MPI, Germany
Computational
Biology provides a wide range of applications for Transfer Learning
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
transfer learning has
been successfully applied. For this, we use regularization based
Transfer Learning 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 Transfer Learning and finally give some practical guidelines, when
MTL strategies
are likely to work.