A Selective Sampling Strategy for Label Ranking
- Cite this paper as:
- Amini M., Usunier N., Laviolette F., Lacasse A., Gallinari P. (2006) A Selective Sampling Strategy for Label Ranking. In: Fürnkranz J., Scheffer T., Spiliopoulou M. (eds) Machine Learning: ECML 2006. ECML 2006. Lecture Notes in Computer Science, vol 4212. Springer, Berlin, Heidelberg
We propose a novel active learning strategy based on the compression framework of  for label ranking functions which, given an input instance, predict a total order over a predefined set of alternatives. Our approach is theoretically motivated by an extension to ranking and active learning of Kääriäinen’s generalization bounds using unlabeled data , initially developed in the context of classification. The bounds we obtain suggest a selective sampling strategy provided that a sufficiently, yet reasonably large initial labeled dataset is provided. Experiments on Information Retrieval corpora from automatic text summarization and question/answering show that the proposed approach allows to substantially reduce the labeling effort in comparison to random and heuristic-based sampling strategies.
Unable to display preview. Download preview PDF.