LAM-PINN clusters PDE tasks via learning-affinity metrics and uses modular subnetworks to cut MSE by 19.7x on unseen tasks while using only 10% of conventional PINN training iterations.
Chakraborty, Transfer learning based multi-fidelity physics informed deep neu- ral network, Journal of Computational Physics 426 (2021) 109942
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compositional Meta-Learning for Mitigating Task Heterogeneity in Physics-Informed Neural Networks
LAM-PINN clusters PDE tasks via learning-affinity metrics and uses modular subnetworks to cut MSE by 19.7x on unseen tasks while using only 10% of conventional PINN training iterations.