mlsanityData to 7 Oct 2026

Feasibility Study on Active Learning of Smart Surrogates for Scientific Simulations

arXiv 2407.07674 ↗First posted 10 Jul 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

High-performance scientific simulations, important for comprehension of complex systems, encounter computational challenges especially when exploring extensive parameter spaces. There has been an increasing interest in developing deep neural networks (DNNs) as surrogate models capable of accelerating the simulations. However, existing approaches for training these DNN surrogates rely on extensive simulation data which are heuristically selected and generated with expensive computation -- a challenge under-explored in the literature. In this paper, we investigate the potential of incorporating active learning into DNN surrogate training. This allows intelligent and objective selection of training simulations, reducing the need to generate extensive simulation data as well as the dependency of the performance of DNN surrogates on pre-defined training simulations. In the problem context of constructing DNN surrogates for diffusion equations with sources, we examine the efficacy of diversity- and uncertainty-based strategies for selecting training simulations, considering two different DNN architecture. The results set the groundwork for developing the high-performance computing infrastructure for Smart Surrogates that supports on-the-fly generation of simulation data steered by active learning strategies to potentially improve the efficiency of scientific simulations.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 10 Jul 2024.

Builds on

34 of 58 references.

References · 34

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  4. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  5. 2017Solving high-dimensional partial differential equations using deep learningcited by 549
  6. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  7. 2019Learning Loss for Active Learningcited by 335
  8. 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 190
  9. 2020PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domaincited by 173
  10. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 165
  11. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
  12. 2017VAMPnets: Deep learning of molecular kineticscited by 135
22 more
  1. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
  2. 2017Deep Active Learning over the Long Tailcited by 82
  3. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 53
  4. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  5. 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
  6. 2020Building high accuracy emulators for scientific simulations with deep neural architecture searchcited by 36
  7. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  8. 2020Active learning of deep surrogates for PDEs: Application to metasurface designcited by 28
  9. 2017Deep Learning the Physics of Transport Phenomenacited by 26
  10. 2020Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networkscited by 26
  11. 2017CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networkscited by 17
  12. 2019DeepDriveMD: Deep-Learning Driven Adaptive Molecular Simulations for Protein Foldingcited by 15
  13. 2020An unsupervised learning approach to solving heat equations on chip based on Auto Encoder and Image Gradientcited by 13
  14. 2019Learning Everywhere: A Taxonomy for the Integration of Machine Learning and Simulationscited by 7
  15. 2021A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexitycited by 7
  16. 2021Deep Bayesian Active Learning for Accelerating Stochastic Simulationcited by 7
  17. 2019Learning Everywhere: Pervasive Machine Learning for Effective High-Performance Computationcited by 6
  18. 2023Efficient Neural PDE-Solvers using Quantization Aware Trainingcited by 6
  19. 2021Deep learning approaches to surrogates for solving the diffusion equation for mechanistic real-world simulationscited by 5
  20. 2023Analyzing the Performance of Deep Encoder-Decoder Networks as Surrogates for a Diffusion Equationcited by 4
  21. 2020Regression Enrichment Surfaces: a Simple Analysis Technique for Virtual Drug Screening Modelscited by 3
  22. 2019Understanding ML driven HPC: Applications and Infrastructurecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Active Learning for Neural PDE Solverscited by 22
  2. 2025Active Learning with Selective Time-Step Acquisition for PDEscited by 4
  3. 2026Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Trainingcited by 1
  4. 2026Data-Efficient Neural Operator Training via Physics-Based Active Learningcited by 0