Domain Agnostic Fourier Neural Operators
Authors: Ning Liu, Siavash Jafarzadeh, Yue Yu
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In our empirical evaluation, DAFNO has achieved state-of-the-art accuracy as compared to baseline neural operator models on two benchmark datasets of material modeling and airfoil simulation. To further demonstrate the capability and generalizability of DAFNO in handling complex domains with topology changes, we consider a brittle material fracture evolution problem. With only one training crack simulation sample, DAFNO has achieved generalizability to unseen loading scenarios and substantially different crack patterns from the trained scenario. Our code and data accompanying this paper are available at https://github.com/ningliu-iga/DAFNO. |
| Researcher Affiliation | Collaboration | Ning Liu Global Engineering and Materials, Inc. Princeton, NJ 08540 ningliu@umich.edu Siavash Jafarzadeh Department of Mathematics Lehigh University Bethlehem, PA 18015 sij222@lehigh.edu Yue Yu Department of Mathematics Lehigh University Bethlehem, PA 18015 yuy214@lehigh.edu |
| Pseudocode | No | The paper includes illustrations of the architecture (Figure 2) and mathematical formulations, but no pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code and data accompanying this paper are available at https://github.com/ningliu-iga/DAFNO. |
| Open Datasets | Yes | For training, we directly adopt the dataset in Li et al. (2022a), where a total of 1000, 200, 200 samples are selected for training, validation and testing, respectively. |
| Dataset Splits | Yes | For training, we directly adopt the dataset in Li et al. (2022a), where a total of 1000, 200, 200 samples are selected for training, validation and testing, respectively. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU models, CPU types, memory). |
| Software Dependencies | No | The paper mentions "2D Peri Fast software (Jafarzadeh et al., 2022a)" but does not specify its version number or any other software dependencies with version numbers. |
| Experiment Setup | Yes | For fair comparison, the hyperparameters of each model are tuned to minimize the error on validation datasets, including initial learning rate, decay rate for every 100 epochs, smoothing parameter, and regularization parameter, while the total number of epochs is restricted to 500 for computational efficiency. |