High Accuracy Uncertainty-Aware Interatomic Force Modeling with Equivariant Bayesian Neural Networks
Not on the map. Why?
Abstract (arXiv)
Even though Bayesian neural networks offer a promising framework for modeling uncertainty, active learning and incorporating prior physical knowledge, few applications of them can be found in the context of interatomic force modeling. One of the main challenges in their application to learning interatomic forces is the lack of suitable Monte Carlo Markov chain sampling algorithms for the posterior density, as the commonly used algorithms do not converge in a practical amount of time for many of the state-of-the-art architectures. As a response to this challenge, we introduce a new Monte Carlo Markov chain sampling algorithm in this paper which can circumvent the problems of the existing sampling methods. In addition, we introduce a new stochastic neural network model based on the NequIP architecture and demonstrate that, when combined with our novel sampling algorithm, we obtain predictions with state-of-the-art accuracy as well as a good measure of uncertainty.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 51 references that are in the map. First posted on arXiv 5 Apr 2023.
Builds on
18 of 51 references.
References · 18
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2016An overview of gradient descent optimization algorithmscited by 1,033
- 2019On the Convergence of Adam and Beyondcited by 841
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
- 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
- 2014Stochastic Gradient Hamiltonian Monte Carlocited by 343
- 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
- 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
- 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
- 2022Graph neural networks for materials science and chemistrycited by 182
- 2015A Complete Recipe for Stochastic Gradient MCMCcited by 146
6 more
- 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 104
- 2019Quality of Uncertainty Quantification for Bayesian Neural Network Inferencecited by 59
- 2021Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistrycited by 30
- 2022Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfallscited by 11
- 2017Nudged elastic band calculations accelerated with Gaussian process regressioncited by 7
- 2018Molecular Dynamics with Neural-Network Potentialscited by 5
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.