A shared-parameter graph U-Net that couples coarse and fine mesh simulations during training predicts high-fidelity PDE solutions more accurately than single-fidelity GNNs or multi-fidelity transfer learning.
Issues in deciding whether to use multifidelity surrogates.Aiaa Journal, 57(5):2039–2054,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Multi-Fidelity Graph U-Net Model for Accelerated Physics Simulations
A shared-parameter graph U-Net that couples coarse and fine mesh simulations during training predicts high-fidelity PDE solutions more accurately than single-fidelity GNNs or multi-fidelity transfer learning.