mlsanityData to 14 Oct 2026

BLIPs: Bayesian Learned Interatomic Potentials

arXiv 2508.14022 ↗First posted 19 Aug 2025cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Machine Learning Interatomic Potentials (MLIPs) are becoming a central tool in simulation-based chemistry. However, like most deep learning models, MLIPs struggle to make accurate predictions on out-of-distribution data or when trained in a data-scarce regime, both common scenarios in simulation-based chemistry. Moreover, MLIPs do not provide uncertainty estimates by construction, which are fundamental to guide active learning pipelines and to ensure the accuracy of simulation results compared to quantum calculations. To address this shortcoming, we propose BLIPs: Bayesian Learned Interatomic Potentials. BLIP is a scalable, architecture-agnostic variational Bayesian framework for training or fine-tuning MLIPs, built on an adaptive version of Variational Dropout. BLIP delivers well-calibrated uncertainty estimates and minimal computational overhead for energy and forces prediction at inference time, while integrating seamlessly with (equivariant) message-passing architectures. Empirical results on simulation-based computational chemistry tasks demonstrate improved predictive accuracy with respect to standard MLIPs, and trustworthy uncertainty estimates, especially in data-scarse or heavy out-of-distribution regimes. Moreover, fine-tuning pretrained MLIPs with BLIP yields consistent performance gains and calibrated uncertainties.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 58 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

32 of 58 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2016Group Equivariant Convolutional Networkscited by 1,165
  7. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  8. 2021E(n) Equivariant Graph Neural Networkscited by 965
  9. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  10. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  11. 2015Weight Uncertainty in Neural Networkscited by 554
  12. 2015Variational Dropout and the Local Reparameterization Trickcited by 490
20 more
  1. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  2. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 443
  3. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  4. 2018Neural Relational Inference for Interacting Systemscited by 339
  5. 2018A General Theory of Equivariant CNNs on Homogeneous Spacescited by 228
  6. 2025UMA: A Family of Universal Models for Atomscited by 105
  7. 2023MatterGen: a generative model for inorganic materials designcited by 98
  8. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 84
  9. 2024Variational Flow Matching for Graph Generationcited by 83
  10. 2024Orb: A Fast, Scalable Neural Network Potentialcited by 66
  11. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 62
  12. 2019Equivariant Flows: sampling configurations for multi-body systems with symmetric energiescited by 57
  13. 2024Open Materials 2024 (OMat24) Inorganic Materials Dataset and Modelscited by 52
  14. 2023Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensemblescited by 30
  15. 2025Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systemscited by 22
  16. 2022Hyperactive Learning (HAL) for Data-Driven Interatomic Potentialscited by 17
  17. 2023Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentialscited by 16
  18. 2022Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfallscited by 11
  19. 2025BARNN: A Bayesian Autoregressive and Recurrent Neural Networkcited by 5
  20. 2025Understanding and Mitigating Distribution Shifts For Machine Learning Force Fieldscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026MADE: Benchmark Environments for Closed-Loop Materials Discoverycited by 7
  2. 2026Knowing when to trust machine-learned interatomic potentialscited by 3
  3. 2026BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Modelscited by 1
  4. 2026Flowing with Confidencecited by 1
  5. 2026AdaptNTK: Adaptive Uncertainty Quantification and Active Learning for Neural Network Potentialscited by 0
  6. 2026Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discoverycited by 0