ERM-based PU classifiers designed for case-control sampling deteriorate under single-sample scenarios, requiring a change in the empirical risk definition; a single-sample analogue of the non-negative risk classifier is introduced and shown to differ notably when many positives are labeled.
Building high-performance classifiers using positive and unlabeled examples for text classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Single-sample versus case-control sampling scheme for Positive Unlabeled data: the story of two scenarios
ERM-based PU classifiers designed for case-control sampling deteriorate under single-sample scenarios, requiring a change in the empirical risk definition; a single-sample analogue of the non-negative risk classifier is introduced and shown to differ notably when many positives are labeled.