SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Models

TL;DR

SCRIB introduces a set-classifier with class-specific risk bounds for black-box models, enabling risk-controlled predictions with rejection options, validated on medical datasets with improved risk accuracy.

Contribution

It proposes a novel set-classifier method that controls class-specific risks with theoretical guarantees, addressing limitations of existing rejection-based classifiers.

Findings

Achieved class-specific risks 35-88% closer to targets.

Validated on EEG, X-ray, and ECG datasets.

Improved risk control over baseline methods.

Abstract

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.