Active learning in parallel universes

Authors:
Nicolas Cebron;Michael R. Berthold
Affiliations:
University of Augsburg, Augsburg, Germany;University of Konstanz, Konstanz, Germany
Venue:
CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
Year:
2010

Citing 6
Cited 1

Improving Generalization with Active Learning

Machine Learning - Special issue on structured connectionist systems
Selective Sampling Using the Query by Committee Algorithm

Machine Learning
Machine Learning

Machine Learning
Feature Selection for Knowledge Discovery and Data Mining

Feature Selection for Knowledge Discovery and Data Mining
Active learning with multiple views

Journal of Artificial Intelligence Research
Learning in parallel universes

Data Mining and Knowledge Discovery

Multi-domain active learning for text classification

Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work addresses two challenges in combination: learning with a very limited number of labeled training examples (active learning) and learning in the presence of multiple views for each object where the global model to be learned is spread out over some or all of these views (learning in parallel universes). We propose a new active learning approach which selects the best samples to query the label with the goal of improving overall model accuracy and determining which universe contributes most to the local model. The resulting combination and class-specific weighting of universes provides a significantly better classification accuracy than traditional active learning methods.