mlsanityData to 7 Oct 2026

A General Approach for Determining Applicability Domain of Machine Learning Models

arXiv 2406.05143 ↗First posted 28 May 2024cond-mat.mtrl-sci cond-mat.other cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 11 of its 52 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

11 of 52 references.

References · 11

  1. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  3. 2020Parametric UMAP embeddings for representation and semi-supervised learningcited by 103
  4. 2023Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineeringcited by 86
  5. 2020Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithmscited by 34
  6. 2017Machine learning modeling of superconducting critical temperaturecited by 32
  7. 2015Evading the curse of dimensionality in nonparametric density estimation with simplified vine copulascited by 18
  8. 2017High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimatescited by 14
  9. 2021ADAPT : Awesome Domain Adaptation Python Toolboxcited by 13
  10. 2023Clarifying Trust of Materials Property Predictions using Neural Networks with Distribution-Specific Uncertainty Quantificationcited by 8
  11. 2023Outlier-Based Domain of Applicability Identification for Materials Property Prediction Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Known Unknowns: Out-of-Distribution Property Prediction in Materials and Moleculescited by 7
  2. 2026A Critical Examination of Active Learning Workflows in Materials Sciencecited by 0
  3. 2026Inferential Mechanics Part 1: Causal Mechanistic Theories of Machine Learning in Chemical Biology with Implicationscited by 0
  4. 2026Uncertainty-aware reinforcement learning for chemical language modelscited by 0
  5. 2026Physics-residual machine learning predicts oxygen-evolution catalyst activity beyond the training range from sparse polarization measurementscited by 0