PINNfluence: Interpreting PINNs through Influence Functions

arXiv:2409.08958 · cs.LG, cs.AI, physics.comp-ph, physics.flu-dyn · Submitted 2024-09-13 · Read on arXiv

cs.LG, cs.AI, physics.comp-ph, physics.flu-dyn

Submitted: 2024-09-13

Updated: 2026-06-02

Terminology

• Influence Functions — 3× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Physics-Informed Neural Networks (PINNs) — 1× in this paper · explained in 8 episodes
• Training Objective — 1× in this paper · explained in 3 episodes
• Training Objectives — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks