Interpretable Fine-Tuning and Error Indication for Graph Neural Network Surrogate Models
- URL: http://arxiv.org/abs/2311.07548v3
- Date: Sat, 29 Jun 2024 21:23:44 GMT
- Title: Interpretable Fine-Tuning and Error Indication for Graph Neural Network Surrogate Models
- Authors: Shivam Barwey, Hojin Kim, Romit Maulik,
- Abstract summary: This work introduces an interpretable fine-tuning strategy for graph neural networks (GNNs)
The end result is an enhanced fine-tuned model that isolates regions in physical space, corresponding to sub-graphs, that are intrinsically linked to the forecasting task.
The fine-tuned GNNs can also be used to identify, during inference, graph nodes that correspond to a majority of the anticipated forecasting error.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Data-driven surrogate modeling has surged in capability in recent years with the emergence of graph neural networks (GNNs), which can operate directly on mesh-based representations of data. The goal of this work is to introduce an interpretable fine-tuning strategy for GNNs, with application to unstructured mesh-based fluid dynamics modeling. The end result is an enhanced fine-tuned model that isolates regions in physical space, corresponding to sub-graphs, that are intrinsically linked to the forecasting task while retaining the predictive capability of the baseline. These structures, identified by the fine-tuned GNNs, are adaptively produced in the forward pass and serve as explainable links between the baseline model architecture, the optimization goal, and known problem-specific physics. Additionally, through a regularization procedure, the fine-tuned GNNs can also be used to identify, during inference, graph nodes that correspond to a majority of the anticipated forecasting error, adding a novel interpretable error-tagging capability to baseline models. Demonstrations are performed using unstructured flow field data sourced from flow over a backward-facing step at high Reynolds numbers, with geometry extrapolations demonstrated for ramp and wall-mounted cube configurations.
Related papers
- Identification of vortex in unstructured mesh with graph neural networks [0.0]
We present a Graph Neural Network (GNN) based model with U-Net architecture to identify the vortex in CFD results on unstructured meshes.
A vortex auto-labeling method is proposed to label vortex regions in 2D CFD meshes.
arXiv Detail & Related papers (2023-11-11T12:10:16Z) - MuseGNN: Interpretable and Convergent Graph Neural Network Layers at
Scale [15.93424606182961]
We propose a sampling-based energy function and scalable GNN layers that iteratively reduce it, guided by convergence guarantees in certain settings.
We also instantiate a full GNN architecture based on these designs, and the model achieves competitive accuracy and scalability when applied to the largest publicly-available node classification benchmark exceeding 1TB in size.
arXiv Detail & Related papers (2023-10-19T04:30:14Z) - Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous
Graph Diffusion Functionals [7.6435511285856865]
Graph neural networks (GNNs) are widely used in domains like social networks and biological systems.
locality assumption of GNNs hampers their ability to capture long-range dependencies and global patterns in graphs.
We propose a new inductive bias based on variational analysis, drawing inspiration from the Brachchronistoe problem.
arXiv Detail & Related papers (2023-07-01T04:44:43Z) - Dynamic Causal Explanation Based Diffusion-Variational Graph Neural
Network for Spatio-temporal Forecasting [60.03169701753824]
We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting.
The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
arXiv Detail & Related papers (2023-05-16T11:38:19Z) - Dynamic Graph Neural Network with Adaptive Edge Attributes for Air
Quality Predictions [12.336689498639366]
We propose a novel Dynamic Graph Neural Network with Adaptive Edge Attributes (DGN-AEA) on the message passing network.
Unlike prior information to establish edges, our method can obtain adaptive edge information through end-to-end training without any prior information.
arXiv Detail & Related papers (2023-02-20T13:45:55Z) - Learnable Filters for Geometric Scattering Modules [64.03877398967282]
We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms.
Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
arXiv Detail & Related papers (2022-08-15T22:30:07Z) - EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural
Networks [51.42338058718487]
Graph Neural Networks (GNNs) have received extensive research attention for their promising performance in graph machine learning.
Existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs.
We propose EvenNet, a spectral GNN corresponding to an even-polynomial graph filter.
arXiv Detail & Related papers (2022-05-27T10:48:14Z) - Continuous-Depth Neural Models for Dynamic Graph Prediction [16.89981677708299]
We introduce the framework of continuous-depth graph neural networks (GNNs)
Neural graph differential equations (Neural GDEs) are formalized as the counterpart to GNNs.
Results prove the effectiveness of the proposed models across applications, such as traffic forecasting or prediction in genetic regulatory networks.
arXiv Detail & Related papers (2021-06-22T07:30:35Z) - Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms.
Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
arXiv Detail & Related papers (2020-10-06T01:20:27Z) - A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data.
In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem.
We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
arXiv Detail & Related papers (2020-10-05T04:57:18Z) - Binarized Graph Neural Network [65.20589262811677]
We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters.
Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches.
Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
arXiv Detail & Related papers (2020-04-19T09:43:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.