SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Models
It addresses the need for reliable rejection options in classification for medical domains, but is incremental as it builds on existing classification with rejection frameworks.
The paper tackled the problem of deep learning classifiers lacking a mechanism to decide when to refrain from predicting, particularly overlooking different class significances, by introducing SCRIB, a set-classifier with class-specific risk bounds, which achieved class-specific risks 35%-88% closer to target risks than baselines in medical applications.
Despite deep learning (DL) success in classification problems, DL classifiers do not provide a sound mechanism to decide when to refrain from predicting. Recent works tried to control the overall prediction risk with classification with rejection options. However, existing works overlook the different significance of different classes. We introduce Set-classifier with Class-specific RIsk Bounds (SCRIB) to tackle this problem, assigning multiple labels to each example. Given the output of a black-box model on the validation set, SCRIB constructs a set-classifier that controls the class-specific prediction risks with a theoretical guarantee. The key idea is to reject when the set classifier returns more than one label. We validated SCRIB on several medical applications, including sleep staging on electroencephalogram (EEG) data, X-ray COVID image classification, and atrial fibrillation detection based on electrocardiogram (ECG) data. SCRIB obtained desirable class-specific risks, which are 35\%-88\% closer to the target risks than baseline methods.