GCN-FFNN: A two-stream deep model for learning solution to partial differential equations
| Autor: | Onur Bilgin, Thomas Vergutz, Siamak Mehrkanoon |
|---|---|
| Přispěvatelé: | RS: FSE DACS, Dept. of Advanced Computing Sciences, RS: FSE DACS Mathematics Centre Maastricht |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
I.2
FOS: Computer and information sciences NUMERICAL-SOLUTION Computer Science - Machine Learning Graph convolutional neural network Cognitive Neuroscience G.1 FOS: Physical sciences Collocation nodes Numerical Analysis (math.NA) Computational Physics (physics.comp-ph) Partial differential equations Representation learning Computer Science Applications Machine Learning (cs.LG) Artificial Intelligence FOS: Mathematics Mathematics - Numerical Analysis NEURAL-NETWORKS ALGORITHM Physics - Computational Physics |
| Zdroj: | Neurocomputing, 511, 131-141. Elsevier Science |
| ISSN: | 0925-2312 |
| Popis: | This paper introduces a novel two-stream deep model based on graph convolutional network (GCN) architecture and feed-forward neural networks (FFNN) for learning the solution of nonlinear partial differential equations (PDEs). The model aims at incorporating both graph and grid input representations using two streams corresponding to GCN and FFNN models, respectively. Each stream layer receives and processes its own input representation. As opposed to FFNN which receives a grid-like structure, the GCN stream layer operates on graph input data where the neighborhood information is incorporated through the adjacency matrix of the graph. In this way, the proposed GCN-FFNN model learns from two types of input representations, i.e. grid and graph data, obtained via the discretization of the PDE domain. The GCN-FFNN model is trained in two phases. In the first phase, the model parameters of each stream are trained separately. Both streams employ the same error function to adjust their parameters by enforcing the models to satisfy the given PDE as well as its initial and boundary conditions on grid or graph collocation (training) data. In the second phase, the learned parameters of two-stream layers are frozen and their learned representation solutions are fed to fully connected layers whose parameters are learned using the previously used error function. The learned GCN-FFNN model is tested on test data located both inside and outside the PDE domain. The obtained numerical results demonstrate the applicability and efficiency of the proposed GCN-FFNN model over individual GCN and FFNN models on 1D-Burgers, 1D-Schr\"odinger, 2D-Burgers and 2D-Schr\"odinger equations. Comment: 10 pages, 10 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect