Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

heterogeneous uncertainty sampling

Heterogeneous uncertainty sampling is an active learning strategy in machine learning where one model is used to identify and select uncertain data points for labeling to train a different target model. In standard uncertainty sampling, the same classifier evaluates the uncertainty of unlabeled instances and learns from the newly labeled data. Heterogeneous uncertainty sampling decouples these roles, typically employing a faster or more computationally efficient proxy algorithm to iteratively select the most informative examples when the primary target classifier is too costly to retrain repeatedly. This approach allows practitioners to minimize manual labeling effort and computational overhead while maintaining high predictive performance in the final target classifier.

1 item

Heterogeneous Uncertainty Sampling for Supervised Learning

Heterogeneous Uncertainty Sampling for Supervised Learning

David D. Lewis, Jason Catlett

OrganizationsAT&T Bell Laboratories

Why you should read this

Demonstrates that using a fast probabilistic classifier to actively select training instances for a more complex C4.5 rule induction model achieves lower error rates on text categorization tasks than random sampling sets ten times larger.

Uncertainty sampling methods iteratively request class labels for training instances whose classes are uncertain despite the previous labeled instances. These methods can greatly reduce the number of instances that an expert need label. One problem with this approach is that the classifier best suited for an application may be too expensive to train or use during the selection of instances. We test the use of one classifier (a highly efficient probabilistic one) to select examples for training another (the C4.5 rule induction program). Despite being chosen by this heterogeneous approach, the uncertainty samples yielded classifiers with lower error rates than random samples ten times larger.

Added

2026-09-25