Sciweavers

Share
CIKM
2008
Springer

Proactive learning: cost-sensitive active learning with multiple imperfect oracles

9 years 11 months ago
Proactive learning: cost-sensitive active learning with multiple imperfect oracles
Proactive learning is a generalization of active learning designed to relax unrealistic assumptions and thereby reach practical applications. Active learning seeks to select the most informative unlabeled instances and ask an omniscient oracle for their labels, so as to retrain the learning algorithm maximizing accuracy. However, the oracle is assumed to be infallible (never wrong), indefatigable (always answers), individual (only one oracle), and insensitive to costs (always free or always charges the same). Proactive learning relaxes all four of these assumptions, relying on a decision-theoretic approach to jointly select the optimal oracle and instance, by casting the problem as a utility optimization problem subject to a budget constraint. Results on multi-oracle optimization over several data sets demonstrate the superiority of our approach over the single-imperfect-oracle baselines in most cases. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning--conce...
Pinar Donmez, Jaime G. Carbonell
Added 12 Oct 2010
Updated 12 Oct 2010
Type Conference
Year 2008
Where CIKM
Authors Pinar Donmez, Jaime G. Carbonell
Comments (0)
books