PICore: Physics-Informed Unsupervised Coreset Selection for Data Efficient Neural Operator Training
Not on the map. Why?
Abstract (arXiv)
Neural operators offer a powerful paradigm for solving partial differential equations (PDEs) that cannot be solved analytically by learning mappings between function spaces. However, there are two main bottlenecks in training neural operators: they require a significant amount of training data to learn these mappings, and this data needs to be labeled, which can only be accessed via expensive simulations with numerical solvers. To alleviate both of these issues simultaneously, we propose PICore, an unsupervised coreset selection framework that identifies the most informative training samples without requiring access to ground-truth PDE solutions. PICore leverages a physics-informed loss to select unlabeled inputs by their potential contribution to operator learning. After selecting a compact subset of inputs, only those samples are simulated using numerical solvers to generate labels, reducing annotation costs. We then train the neural operator on the reduced labeled dataset, significantly decreasing training time as well. Across four diverse PDE benchmarks and multiple coreset selection strategies, PICore achieves up to 78% average increase in training efficiency relative to supervised coreset selection methods with minimal changes in accuracy. We provide code at https://github.com/Asatheesh6561/PICore.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 23 Jul 2025.
Builds on
36 of 54 references.
References · 36
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
- 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 748
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2021Deep Learning on a Data Diet: Finding Important Examples Early in Trainingcited by 529
- 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 516
- 2021Neural Operator: Learning Maps Between Function Spacescited by 413
- 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 396
- 2021GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Trainingcited by 269
- 2021Factorized Fourier Neural Operatorscited by 237
- 2022A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networkscited by 233
- 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 225
24 more
- 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 224
- 2022U-NO: U-shaped Neural Operatorscited by 219
- 2023Convolutional Neural Operators for robust and accurate learning of PDEscited by 207
- 2022DeepCore: A Comprehensive Library for Coreset Selection in Deep Learningcited by 146
- 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
- 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 114
- 2021RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learningcited by 72
- 2022Adaptive Second Order Coresets for Data-efficient Machine Learningcited by 60
- 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
- 2021Learning Dissipative Dynamics in Chaotic Systemscited by 41
- 2019Small-GAN: Speeding Up GAN Training Using Core-setscited by 40
- 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learningcited by 32
- 2022In Defense of Core-set: A Density-aware Core-set Selection for Active Learningcited by 26
- 2021Core-set Sampling for Efficient Neural Architecture Searchcited by 23
- 2023Multi-Resolution Active Learning of Fourier Neural Operatorscited by 22
- 2024Active Learning for Neural PDE Solverscited by 22
- 2018Inexact Non-Convex Newton-Type Methodscited by 11
- 2024Speculative Coreset Selection for Task-Specific Fine-tuningcited by 10
- 2023Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspectivecited by 6
- 2023Understanding Uncertainty Sampling via Equivalent Losscited by 5
- 2023Multi-fidelity Fourier Neural Operator for Fast Modeling of Large-Scale Geological Carbon Storagecited by 5
- 2024Pretraining a Neural Operator in Lower Dimensionscited by 5
- 2024Understanding Uncertainty-based Active Learning Under Model Mismatchcited by 3
- 2023On the Convergence of Loss and Uncertainty-based Active Learning Algorithmscited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.