A novel Deep Learning approach for one-step Conformal Prediction approximation
This work addresses the need for efficient and reliable confidence measures in deep learning for high-risk applications, representing an incremental improvement over existing methods.
The paper tackles the problem of making deep learning predictions with measurable confidence by proposing a novel conformal loss function that approximates the two-step Conformal Prediction framework in a single step, achieving up to 86% training time reduction while maintaining comparable validity and efficiency on benchmark datasets.
Deep Learning predictions with measurable confidence are increasingly desirable for real-world problems, especially in high-risk settings. The Conformal Prediction (CP) framework is a versatile solution that guarantees a maximum error rate given minimal constraints. In this paper, we propose a novel conformal loss function that approximates the traditionally two-step CP approach in a single step. By evaluating and penalising deviations from the stringent expected CP output distribution, a Deep Learning model may learn the direct relationship between the input data and the conformal p-values. We carry out a comprehensive empirical evaluation to show our novel loss function's competitiveness for seven binary and multi-class prediction tasks on five benchmark datasets. On the same datasets, our approach achieves significant training time reductions up to 86% compared to Aggregated Conformal Prediction (ACP), while maintaining comparable approximate validity and predictive efficiency.