Conformal Risk Control for Ordinal Classification
This work addresses risk control for ordinal classification, which is important for applications like medical diagnosis, but is incremental as it extends existing conformal risk control methods to a specific task.
The authors tackled the problem of controlling conformal risk in expectation for ordinal classification tasks, proposing two specialized loss functions and algorithms that demonstrated effectiveness across three datasets including UTKFace and diabetic retinopathy detection.
As a natural extension to the standard conformal prediction method, several conformal risk control methods have been recently developed and applied to various learning problems. In this work, we seek to control the conformal risk in expectation for ordinal classification tasks, which have broad applications to many real problems. For this purpose, we firstly formulated the ordinal classification task in the conformal risk control framework, and provided theoretic risk bounds of the risk control method. Then we proposed two types of loss functions specially designed for ordinal classification tasks, and developed corresponding algorithms to determine the prediction set for each case to control their risks at a desired level. We demonstrated the effectiveness of our proposed methods, and analyzed the difference between the two types of risks on three different datasets, including a simulated dataset, the UTKFace dataset and the diabetic retinopathy detection dataset.