When Does Physics Beat Data? Data-Efficient Traffic State Estimation with Amortized PINNs
cs.LG
Submitted: 2026-11-09
Updated: 2026-11-09
Comments: 8 pages, 5 figures. Accepted at the SSTDM workshop, IEEE ICDM 2026
Code: https://github.com/Davidham3/ASTGCN
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Physics-Informed Deep Learning for Traffic State Estimation
- Loss-Conditional PINNs for Parametric PDE Families
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis