Improving Generalization with Active Learning
Machine Learning - Special issue on structured connectionist systems
On Active Learning for Data Acquisition
ICDM '02 Proceedings of the 2002 IEEE International Conference on Data Mining
Active Sampling for Class Probability Estimation and Ranking
Machine Learning
Active Feature-Value Acquisition for Classifier Induction
ICDM '04 Proceedings of the Fourth IEEE International Conference on Data Mining
An Expected Utility Approach to Active Feature-Value Acquisition
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Feature value acquisition in testing: a sequential batch test algorithm
ICML '06 Proceedings of the 23rd international conference on Machine learning
Active Feature-Value Acquisition
Management Science
Tutorial summary: Active learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
VOILA: efficient feature-value acquisition for classification
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Budgeted learning of nailve-bayes classifiers
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Learning and classifying under hard budgets
ECML'05 Proceedings of the 16th European conference on Machine Learning
| Hi-index | 0.00 |
The problem of intelligently acquiring missing input information given a limited number of queries to enhance classification performance has gained substantial interest in the last decade or so. This is primarily due to the emergence of the targeted advertising industry which is trying to best match products to its potential consumer base in the absence of complete consumer profile information. In this paper, we propose a novel active feature acquisition technique to tackle this problem of instance completion prevalent in these domains. We show theoretically that our technique is optimal given the current classifier and derive a probabilistic lower bound on the error reduction achieved with our technique. We also show that a simplification of our technique is equivalent to the Expected Utility approach which is one of the most sophisticated solutions for this problem in existing literature. We then demonstrate the efficacy of our approach through experiments on real data. Finally, we show that our technique can be easily extended to the scenario where we have a cost matrix associated with acquiring missing information for each instance or instance-feature combinations.