Predictive Inference With Fast Feature Conformal Prediction

TL;DR

This paper introduces Fast Feature Conformal Prediction (FFCP), a computationally efficient method that approximates feature space conformal prediction using Taylor expansion, maintaining accuracy while significantly reducing runtime.

Contribution

The paper proposes FFCP, a novel fast approximation of feature conformal prediction that reduces computational time by about 50 times without sacrificing performance.

Findings

FFCP performs comparably to FCP in accuracy.

FFCP reduces computational time by approximately 50x.

Empirical results validate the effectiveness of FFCP.

Abstract

Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties. In the realm of modern deep learning, researchers have proposed Feature Conformal Prediction (FCP), which deploys conformal prediction in a feature space, yielding reduced band lengths. However, the practical utility of FCP is limited due to the time-consuming non-linear operations required to transform confidence bands from feature space to output space. In this paper, we introduce Fast Feature Conformal Prediction (FFCP), which features a novel non-conformity score and is convenient for practical applications. FFCP serves as a fast version of FCP, in that it equivalently employs a Taylor expansion to approximate the aforementioned non-linear operations in FCP. Empirical validations showcase that FFCP performs comparably with FCP (both outperforming the vanilla version) while achieving a significant reduction in computational time by approximately 50x. The code is available at https://github.com/ElvisWang1111/FastFeatureCP