TGSR-PINN improves PINN inverse-problem transfer learning by scoring neuron relevance to the target task via Taylor sensitivity and pre-activation variance, then applying continuous soft decay to low-scoring neurons rather than hard pruning or random resetting.
Scientific ma- chine learning through physics-informed neural networks: Where we are and what’s next.Journal of Scientific Com- puting, 2022, 92(3): 88
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach
TGSR-PINN improves PINN inverse-problem transfer learning by scoring neuron relevance to the target task via Taylor sensitivity and pre-activation variance, then applying continuous soft decay to low-scoring neurons rather than hard pruning or random resetting.