A General Approach for Determining Applicability Domain of Machine Learning Models

TL;DR

This paper introduces a general kernel density estimation-based method to determine the applicability domain of machine learning models, ensuring reliable predictions across various data sets and model types.

Contribution

It presents a novel, model-agnostic approach for assessing the domain of applicability using feature space dissimilarity measures, validated across multiple datasets.

Findings

Dissimilarity correlates with model performance and uncertainty.

Unrelated chemical groups show significant dissimilarities.

Automated tools help define in-domain versus out-of-domain predictions.

Abstract

Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions. In this work, we develop a new and general approach of assessing model domain and demonstrate that our approach provides accurate and meaningful domain designation across multiple model types and material property data sets. Our approach assesses the distance between data in feature space using kernel density estimation, where this distance provides an effective tool for domain determination. We show that chemical groups considered unrelated based on chemical knowledge exhibit significant dissimilarities by our measure. We also show that high measures of dissimilarity are associated with poor model performance (i.e., high residual magnitudes) and poor estimates of model uncertainty (i.e., unreliable uncertainty estimation). Automated tools are provided to enable researchers to establish acceptable dissimilarity thresholds to identify whether new predictions of their own machine learning models are in-domain versus out-of-domain.