
AutoGraph: Automated Graph Neural Network
Graphs play an important role in many applications. Recently, Graph Neur...
read it

Simple and efficient algorithms for training machine learning potentials to force data
Abstract Machine learning models, trained on data from ab initio quantum...
read it

From Graph LowRank Global Attention to 2FWL Approximation
Graph Neural Networks (GNNs) are known to have an expressive power bound...
read it

Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
Graph Neural Networks (GNNs) have made significant advances on several f...
read it

Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex MultiElement Extended Systems
Neural network force field (NNFF) is a method for performing regression ...
read it

Rotation Invariant Graph Neural Networks using Spin Convolutions
Progress towards the energy breakthroughs needed to combat climate chang...
read it
ForceNet: A Graph Neural Network for LargeScale Quantum Calculations
With massive amounts of atomic simulation data available, there is a huge opportunity to develop fast and accurate machine learning models to approximate expensive physicsbased calculations. The key quantity to estimate is atomic forces, where the stateoftheart Graph Neural Networks (GNNs) explicitly enforce basic physical constraints such as rotationcovariance. However, to strictly satisfy the physical constraints, existing models have to make tradeoffs between computational efficiency and model expressiveness. Here we explore an alternative approach. By not imposing explicit physical constraints, we can flexibly design expressive models while maintaining their computational efficiency. Physical constraints are implicitly imposed by training the models using physicsbased data augmentation. To evaluate the approach, we carefully design a scalable and expressive GNN model, ForceNet, and apply it to OC20 (Chanussot et al., 2020), an unprecedentedlylarge dataset of quantum physics calculations. Our proposed ForceNet is able to predict atomic forces more accurately than stateoftheart physicsbased GNNs while being faster both in training and inference. Overall, our promising and counterintuitive results open up an exciting avenue for future research.
READ FULL TEXT
Comments
There are no comments yet.