Quantifying Local Model Validity using Active Learning

TL;DR

This paper introduces a method to estimate local model validity using active learning, enabling efficient and sensitive validation of machine learning models in regulated applications.

Contribution

It proposes learning a model error for local validity estimation with active learning, reducing data needs and improving sensitivity over existing methods.

Findings

Error model achieves good discrimination with limited data

Method demonstrates increased sensitivity to local validity changes

Empirical results validate effectiveness on validation benchmarks

Abstract

Real-world applications of machine learning models are often subject to legal or policy-based regulations. Some of these regulations require ensuring the validity of the model, i.e., the approximation error being smaller than a threshold. A global metric is generally too insensitive to determine the validity of a specific prediction, whereas evaluating local validity is costly since it requires gathering additional data.We propose learning the model error to acquire a local validity estimate while reducing the amount of required data through active learning. Using model validation benchmarks, we provide empirical evidence that the proposed method can lead to an error model with sufficient discriminative properties using a relatively small amount of data. Furthermore, an increased sensitivity to local changes of the validity bounds compared to alternative approaches is demonstrated.