mlsanityData to 7 Oct 2026

Materials Property Prediction with Uncertainty Quantification: A Benchmark Study

arXiv 2211.02235 ↗First posted 4 Nov 2022cond-mat.mtrl-sci cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Uncertainty quantification (UQ) has increasing importance in building robust high-performance and generalizable materials property prediction models. It can also be used in active learning to train better models by focusing on getting new training data from uncertain regions. There are several categories of UQ methods each considering different types of uncertainty sources. Here we conduct a comprehensive evaluation on the UQ methods for graph neural network based materials property prediction and evaluate how they truly reflect the uncertainty that we want in error bound estimation or active learning. Our experimental results over four crystal materials datasets (including formation energy, adsorption energy, total energy, and band gap properties) show that the popular ensemble methods for uncertainty estimation is NOT the best choice for UQ in materials property prediction. For the convenience of the community, all the source code and data sets can be accessed freely at urlhttps://github.com/usccolumbia/materialsUQ.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 18 of its 75 references that are in the map. First posted on arXiv 4 Nov 2022.

Builds on

18 of 75 references.

References · 18

  1. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  3. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  4. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  5. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  6. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  7. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  8. 2019Deep Evidential Regressioncited by 354
  9. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  10. 2020Uncertainty Quantification Using Neural Networks for Molecular Property Predictioncited by 66
  11. 2021Scalable deeper graph neural networks for high-performance materials property predictioncited by 26
  12. 2021Assigning Confidence to Molecular Property Predictioncited by 14
6 more
  1. 2021Uncertainty Prediction for Machine Learning Models of Material Propertiescited by 10
  2. 2020Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networkscited by 7
  3. 2018Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networkscited by 6
  4. 2020Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Predictioncited by 3
  5. 2018Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Errors for Deep Neural Networkscited by 2
  6. 2021Active learning based generative design for the discovery of wide bandgap materialscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 2; 2025: 4; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensemblescited by 30
  2. 2024Structure-based out-of-distribution (OOD) materials property prediction: a benchmark studycited by 17
  3. 2023Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivitycited by 13
  4. 2023MUBen: Benchmarking the Uncertainty of Molecular Representation Modelscited by 11
  5. 2023Validation of uncertainty quantification metrics: a primer based on the consistency and adaptivity conceptscited by 5
  6. 2024Improved Uncertainty Estimation of Graph Neural Network Potentials Using Engineered Latent Space Distancescited by 3
  7. 2022Composition based oxidation state prediction of materials using deep learningcited by 1
  8. 2025Uncertainty Quantification in Graph Neural Networks with Shallow Ensemblescited by 1
  9. 2025Aligning Reasoning LLMs for Materials Discovery with Physics-aware Rejection Samplingcited by 1
  10. 2025Benchmarking GNNs for OOD Materials Property Prediction with Uncertainty Quantificationcited by 1
  11. 2025When Active Learning Fails, Uncalibrated Out of Distribution Uncertainty Quantification Might Be the Problemcited by 1
  12. 2026A Critical Examination of Active Learning Workflows in Materials Sciencecited by 0
2 more
  1. 2026Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?cited by 0
  2. 2026Distribution-Free Conformal Prediction for Steel Fatigue Strength: Marginal Validity Is Not Enoughcited by 0