Trainable Adaptive Activation Function Structure (TAAFS) Enhances Neural Network Force Field Performance with Only Dozens of Additional Parameters
This work addresses the need for more efficient and precise force fields in computational chemistry and materials science, though it appears incremental as it builds on existing NNFF methods with a novel activation function approach.
The paper tackles the problem of improving neural network force fields (NNFFs) without significantly increasing parameter counts by introducing the Trainable Adaptive Activation Function Structure (TAAFS), which selects distinct mathematical formulations for non-linear activations, resulting in observed accuracy improvements validated through molecular dynamics simulations.
At the heart of neural network force fields (NNFFs) is the architecture of neural networks, where the capacity to model complex interactions is typically enhanced through widening or deepening multilayer perceptrons (MLPs) or by increasing layers of graph neural networks (GNNs). These enhancements, while improving the model's performance, often come at the cost of a substantial increase in the number of parameters. By applying the Trainable Adaptive Activation Function Structure (TAAFS), we introduce a method that selects distinct mathematical formulations for non-linear activations, thereby increasing the precision of NNFFs with an insignificant addition to the parameter count. In this study, we integrate TAAFS into a variety of neural network models, resulting in observed accuracy improvements, and further validate these enhancements through molecular dynamics (MD) simulations using DeepMD.