Deep learning and multi-level featurization of graph representations of microstructural data
Not on the map. Why?
Abstract (arXiv)
Many material response functions depend strongly on microstructure, such as inhomogeneities in phase or orientation. Homogenization presents the task of predicting the mean response of a sample of the microstructure to external loading for use in subgrid models and structure-property explorations. Although many microstructural fields have obvious segmentations, learning directly from the graph induced by the segmentation can be difficult because this representation does not encode all the information of the full field. We develop a means of deep learning of hidden features on the reduced graph given the native discretization and a segmentation of the initial input field. The features are associated with regions represented as nodes on the reduced graph. This reduced representation is then the basis for the subsequent multi-level/scale graph convolutional network model. There are a number of advantages of reducing the graph before fully processing with convolutional layers it, such as interpretable features and efficiency on large meshes. We demonstrate the performance of the proposed network relative to convolutional neural networks operating directly on the native discretization of the data using three physical exemplars.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 64 references that are in the map. First posted on arXiv 29 Sep 2022.
Builds on
25 of 64 references.
References · 25
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2016Variational Graph Auto-Encoderscited by 1,382
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
- 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
- 2019Graph U-Netscited by 492
- 2017Representation Learning on Graphs: Methods and Applicationscited by 457
13 more
- 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
- 2015Understanding Neural Networks Through Deep Visualizationcited by 334
- 2020A Survey on Neural Network Interpretabilitycited by 291
- 2016Model-Agnostic Interpretability of Machine Learningcited by 219
- 2019Graph Neural Networks with convolutional ARMA filterscited by 185
- 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
- 2021Understanding Pooling in Graph Neural Networkscited by 69
- 2020Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticitycited by 49
- 2022GNN-Surrogate: A Hierarchical and Adaptive Graph Neural Network for Parameter Space Exploration of Unstructured-Mesh Ocean Simulationscited by 32
- 2020Graph Convolutional Neural Networks for Body Force Predictioncited by 16
- 2021Mesh-based graph convolutional neural networks for modeling materials with microstructurecited by 7
- 2022Learning the nonlinear dynamics of soft mechanical metamaterials with graph networkscited by 7
- 2018Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional networkcited by 6
Built on by
Citing papers per year: 2024: 2.
2 papers.