We extend the classical single-task active learning (AL) approach. In the multi-task active learning (MTAL) paradigm, we select examples for several annotation tasks rather than f...
Roi Reichart, Katrin Tomanek, Udo Hahn, Ari Rappop...
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
The paper evaluates the eectiveness of learning for speeding up the solution of constraint satisfaction problems. It extends previous work (Dechter 1990) by introducing a new and ...
We study the problem of learning parity functions that depend on at most k variables (kparities) attribute-efficiently in the mistake-bound model. We design a simple, deterministi...
Label ranking studies the problem of learning a mapping from instances to rankings over a predefined set of labels. Hitherto existing approaches to label ranking implicitly operat...