Improved Uncertainty Estimation of Graph Neural Network Potentials Using Engineered Latent Space Distances
JOURNAL OF PHYSICAL CHEMISTRY C(2024)
Carnegie Mellon Univ | Meta Platforms Inc
Abstract
Graph neural networks (GNNs) have been shown to be astonishingly capable models for molecular property prediction, particularly as surrogates for expensive density functional theory calculations of relaxed energy for novel material discovery. However, one limitation of GNNs in this context is the lack of useful uncertainty prediction methods, as this is critical to the material discovery pipeline. In this work, we show that uncertainty quantification for relaxed energy calculations is more complex than uncertainty quantification for other kinds of molecular property prediction due to the effect that structure optimizations have on the error distribution. We propose that distribution-free techniques are more useful tools for assessing calibration, recalibrating, and developing uncertainty prediction methods for GNNs performing relaxed energy calculations. We also develop a relaxed energy task for evaluating uncertainty methods for equivariant GNNs, based on distribution-free recalibration and using the Open Catalyst Project data set. We benchmark a set of popular uncertainty prediction methods on this task and show that conformal prediction methods, with our novel latent space distance improvements, are the most well-calibrated and efficient approach for relaxed energy calculations. Finally, we demonstrate that our latent space distance method produces results which align with our expectations on an atom clustering example, and on specific equation of state and adsorbate coverage examples from outside the training data set.
MoreTranslated text
PDF
View via Publisher
AI Read Science
Must-Reading Tree
Example

Generate MRT to find the research sequence of this paper
Related Papers
2013
被引用5016 | 浏览
2013
被引用12 | 浏览
2013
被引用23 | 浏览
2015
被引用53 | 浏览
2018
被引用2287 | 浏览
2017
被引用2265 | 浏览
2018
被引用31 | 浏览
2017
被引用268 | 浏览
2019
被引用37 | 浏览
2019
被引用278 | 浏览
2020
被引用116 | 浏览
2020
被引用30 | 浏览
2020
被引用28 | 浏览
2021
被引用22 | 浏览
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
去 AI 文献库 对话