mlsanityData to 7 Oct 2026

BARNN: A Bayesian Autoregressive and Recurrent Neural Network

arXiv 2501.18665 ↗First posted 30 Jan 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Autoregressive and recurrent networks have achieved remarkable progress across various fields, from weather forecasting to molecular generation and Large Language Models. Despite their strong predictive capabilities, these models lack a rigorous framework for addressing uncertainty, which is key in scientific applications such as PDE solving, molecular generation and Machine Learning Force Fields. To address this shortcoming we present BARNN: a variational Bayesian Autoregressive and Recurrent Neural Network. BARNNs aim to provide a principled way to turn any autoregressive or recurrent model into its Bayesian version. BARNN is based on the variational dropout method, allowing to apply it to large recurrent neural networks as well. We also introduce a temporal version of the "Variational Mixtures of Posteriors" prior (tVAMP-prior) to make Bayesian inference efficient and well-calibrated. Extensive experiments on PDE modelling and molecular generation demonstrate that BARNN not only achieves comparable or superior accuracy compared to existing methods, but also excels in uncertainty quantification and modelling long-range dependencies.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 60 references that are in the map. First posted on arXiv 30 Jan 2025.

Builds on

33 of 60 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  7. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  8. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 516
  9. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  10. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  11. 2022Message Passing Neural PDE Solverscited by 368
  12. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
21 more
  1. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  2. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 261
  3. 2020Model Reduction and Neural Networks for Parametric PDEscited by 257
  4. 2017VAE with a VampPriorcited by 247
  5. 2018Learning Deep Generative Models of Graphscited by 227
  6. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 205
  7. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  8. 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
  9. 2023Bayesian Low-rank Adaptation for Large Language Modelscited by 112
  10. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  11. 2016Neural Autoregressive Distribution Estimationcited by 94
  12. 2020Bayesian Bits: Unifying Quantization and Pruningcited by 93
  13. 2024Variational Flow Matching for Graph Generationcited by 78
  14. 2022Lie Point Symmetry Data Augmentation for Neural PDE Solverscited by 76
  15. 2023Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulationcited by 65
  16. 2020Reinforcement Learning for Molecular Design Guided by Quantum Mechanicscited by 51
  17. 2015Bayesian Dark Knowledgecited by 45
  18. 2023A graph convolutional autoencoder approach to model order reduction for parametrized PDEscited by 44
  19. 2024Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequencescited by 13
  20. 2023Generative Adversarial Reduced Order Modellingcited by 7
  21. 2018Variational Dropout via Empirical Bayescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025BLIPs: Bayesian Learned Interatomic Potentialscited by 6
  2. 2025Single- to multi-fidelity history-dependent learning with uncertainty quantification and disentanglement: application to data-driven constitutive modelingcited by 1
  3. 2026Tuning the burn-in phase in training recurrent neural networks improves their performancecited by 1
  4. 2026BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Modelscited by 1
  5. 2026Flowing with Confidencecited by 0