Adaptive Physics-informed Neural Networks: A Survey
Authors: Edgar Torres, Mathias Niepert
TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This survey reviews existing research that addresses these limitations through transfer learning and meta-learning. The covered methods improve the training efficiency, allowing faster adaptation to new PDEs with fewer data and computational resources. While the paper includes "Table 7: Comparison of PINN methods" which synthesizes results from other works, it does not conduct new empirical studies or experiments itself. |
| Researcher Affiliation | Collaboration | Edgar Torres EMAIL Institute for Artificial Intelligence University of Stuttgart; Jonathan Schiefer EMAIL Robert Bosch Gmb H, Stuttgart; Mathias Niepert EMAIL Institute for Artificial Intelligence University of Stuttgart. The affiliations include both academic institutions (University of Stuttgart) and an industry entity (Robert Bosch GmbH). |
| Pseudocode | No | The paper describes various methods and techniques (e.g., MAML, Reptile, SVD-PINNs) within the surveyed literature but does not include any structured pseudocode or algorithm blocks for these or any other procedures. |
| Open Source Code | No | The paper is a survey and does not present new methodology that would require code release. There is no mention of a code repository or an explicit statement about the availability of source code for the survey itself. |
| Open Datasets | No | The paper is a survey and analyzes existing literature on adaptive PINNs. While it discusses benchmark PDE problems used in other studies (e.g., Burgers equation, Poisson equation), it does not conduct its own experiments requiring specific datasets and thus does not provide concrete access information for any dataset used in this paper's analysis. |
| Dataset Splits | No | This paper is a survey and review of existing literature, not an experimental paper. Therefore, it does not involve the use or splitting of datasets for its own empirical evaluation. |
| Hardware Specification | No | The paper is a survey and does not describe any specific hardware used for conducting experiments or analysis within the scope of this work. It discusses computational efficiency in general terms but does not provide hardware specifications for its own research. |
| Software Dependencies | No | The paper mentions several software tools and libraries (e.g., JAX, XLB, Diffrax) that are relevant to the methods discussed in the surveyed literature. However, it does not specify any particular software dependencies with version numbers used to conduct the research or prepare the findings of this survey paper. |
| Experiment Setup | No | As a survey paper, this work analyzes and synthesizes findings from other research. It does not present its own experimental results, and therefore, there is no experimental setup or hyperparameter information provided for this paper's methodology. |