AnisoGNN: Physics-Informed Graph Neural Networks That Generalize to Anisotropic Properties of Polycrystals
Abstract
We present AnisoGNNs -- graph neural networks (GNNs) that generalize predictions of anisotropic properties of polycrystals in arbitrary testing directions without the need in excessive training data. To this end, we develop GNNs with a physics-inspired combination of node attributes and aggregation function. We demonstrate the excellent generalization capabilities of AnisoGNNs in predicting anisotropic elastic and inelastic properties of two alloys.
Cite
Text
Hu and Latypov. "AnisoGNN: Physics-Informed Graph Neural Networks That Generalize to Anisotropic Properties of Polycrystals." NeurIPS 2023 Workshops: AI4Mat, 2023.Markdown
[Hu and Latypov. "AnisoGNN: Physics-Informed Graph Neural Networks That Generalize to Anisotropic Properties of Polycrystals." NeurIPS 2023 Workshops: AI4Mat, 2023.](https://mlanthology.org/neuripsw/2023/hu2023neuripsw-anisognn/)BibTeX
@inproceedings{hu2023neuripsw-anisognn,
title = {{AnisoGNN: Physics-Informed Graph Neural Networks That Generalize to Anisotropic Properties of Polycrystals}},
author = {Hu, Guangyu and Latypov, Marat},
booktitle = {NeurIPS 2023 Workshops: AI4Mat},
year = {2023},
url = {https://mlanthology.org/neuripsw/2023/hu2023neuripsw-anisognn/}
}