AUC Maximization from Biased Positive-unlabeled Data with Confidence
This paper derives an estimator of the AUC risk using biased PU data with confidence, enabling AUC maximization under such bias, and shows that the rewritten AUC risk induces a Bayes-optimal AUC ranking even when the available confidence is any strictly increasing transformation of the true posterior probability.
Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi et al.
· 0 citations