Efficient physics-informed neural networks using hash encoding
This work addresses efficiency bottlenecks for researchers and practitioners using PINNs in scientific computing, though it is incremental as it builds on existing encoding techniques from neural representation fields.
The authors tackled the high training cost of physics-informed neural networks (PINNs) by incorporating multi-resolution hash encoding, achieving about a 10-fold improvement in efficiency over vanilla PINNs on problems like Burgers, Helmholtz, and Navier-Stokes equations.
Physics-informed neural networks (PINNs) have attracted a lot of attention in scientific computing as their functional representation of partial differential equation (PDE) solutions offers flexibility and accuracy features. However, their training cost has limited their practical use as a real alternative to classic numerical methods. Thus, we propose to incorporate multi-resolution hash encoding into PINNs to improve the training efficiency, as such encoding offers a locally-aware (at multi resolution) coordinate inputs to the neural network. Borrowed from the neural representation field community (NeRF), we investigate the robustness of calculating the derivatives of such hash encoded neural networks with respect to the input coordinates, which is often needed by the PINN loss terms. We propose to replace the automatic differentiation with finite-difference calculations of the derivatives to address the discontinuous nature of such derivatives. We also share the appropriate ranges for the hash encoding hyperparameters to obtain robust derivatives. We test the proposed method on three problems, including Burgers equation, Helmholtz equation, and Navier-Stokes equation. The proposed method admits about a 10-fold improvement in efficiency over the vanilla PINN implementation.