On Training Derivative-Constrained Neural Networks
This work addresses training challenges in physics-informed neural networks for scientific applications, but it appears incremental as it builds on existing methods with modifications.
The paper tackles the problem of training neural networks with derivative constraints, common in physics-informed settings, by proposing an integrated ReLU activation function and stabilization techniques, resulting in improved incorporation of derivative training signals.
We refer to the setting where the (partial) derivatives of a neural network's (NN's) predictions with respect to its inputs are used as additional training signal as a derivative-constrained (DC) NN. This situation is common in physics-informed settings in the natural sciences. We propose an integrated RELU (IReLU) activation function to improve training of DC NNs. We also investigate denormalization and label rescaling to help stabilize DC training. We evaluate our methods on physics-informed settings including quantum chemistry and Scientific Machine Learning (SciML) tasks. We demonstrate that existing architectures with IReLU activations combined with denormalization and label rescaling better incorporate training signal provided by derivative constraints.