Spherical Channels for Modeling Atomic Interactions

• URL: http://arxiv.org/abs/2206.14331v1
• Date: Wed, 29 Jun 2022 00:03:14 GMT
• Title: Spherical Channels for Modeling Atomic Interactions
• Authors: C. Lawrence Zitnick, Abhishek Das, Adeesh Kolluru, Janice Lan, Muhammed Shuaibi, Anuroop Sriram, Zachary Ulissi, Brandon Wood
• Abstract summary: We propose the Spherical Channel Network (SCN) to model atomic energies and forces. SCN is a graph neural network where nodes represent atoms and edges their neighboring atoms. We demonstrate results on the large-scale Open Catalyst 2020 dataset in both energy and force prediction for numerous tasks and metrics.
• Score: 11.44635961607696
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modeling the energy and forces of atomic systems is a fundamental problem in computational chemistry with the potential to help address many of the world's most pressing problems, including those related to energy scarcity and climate change. These calculations are traditionally performed using Density Functional Theory, which is computationally very expensive. Machine learning has the potential to dramatically improve the efficiency of these calculations from days or hours to seconds. We propose the Spherical Channel Network (SCN) to model atomic energies and forces. The SCN is a graph neural network where nodes represent atoms and edges their neighboring atoms. The atom embeddings are a set of spherical functions, called spherical channels, represented using spherical harmonics. We demonstrate, that by rotating the embeddings based on the 3D edge orientation, more information may be utilized while maintaining the rotational equivariance of the messages. While equivariance is a desirable property, we find that by relaxing this constraint in both message passing and aggregation, improved accuracy may be achieved. We demonstrate state-of-the-art results on the large-scale Open Catalyst 2020 dataset in both energy and force prediction for numerous tasks and metrics.

Related papers

• Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations [58.130170155147205]
  Neural wave functions accomplished unprecedented accuracies in approximating the ground state of many-electron systems, though at a high computational cost. Recent works proposed amortizing the cost by learning generalized wave functions across different structures and compounds instead of solving each problem independently. This work tackles the problem by defining overparametrized, fully learnable neural wave functions suitable for generalization across molecules.
  arXiv  Detail & Related papers  (2024-05-23T16:30:51Z)
• Neural Astrophysical Wind Models [0.0]
  We show that deep neural networks embedded as individual terms in the governing coupled ordinary differential equations (ODEs) can robustly discover both of these physics. We optimize a loss function based on the Mach number, rather than the explicitly solved-for 3 conserved variables, and apply a penalty term towards near-diverging solutions. This work further highlights the feasibility of neural ODEs as a promising discovery tool with mechanistic interpretability for non-linear inverse problems.
  arXiv  Detail & Related papers  (2023-06-20T16:37:57Z)
• Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction [63.4049850776926]
  A crystal structure consists of a minimal unit cell that is repeated infinitely in 3D space. Current methods construct graphs by establishing edges only between nearby nodes. We propose to model physics-principled interatomic potentials directly instead of only using distances.
  arXiv  Detail & Related papers  (2023-06-12T07:19:01Z)
• KineticNet: Deep learning a transferable kinetic energy functional for orbital-free density functional theory [13.437597619451568]
  KineticNet is an equivariant deep neural network architecture based on point convolutions adapted to the prediction of quantities on molecular quadrature grids. For the first time, chemical accuracy of the learned functionals is achieved across input densities and geometries of tiny molecules.
  arXiv  Detail & Related papers  (2023-05-08T17:43:31Z)
• Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling [51.83761266429285]
  We propose a novel Transformer architecture that takes nodes (atoms) and edges (bonds and nonbonding atom pairs) as inputs and models the interactions among them. Moleformer achieves state-of-the-art on the initial state to relaxed energy prediction of OC20 and is very competitive in QM9 on predicting quantum chemical properties.
  arXiv  Detail & Related papers  (2023-02-02T03:49:57Z)
• Rotation Invariant Graph Neural Networks using Spin Convolutions [28.4962005849904]
  Machine learning approaches have the potential to approximate Density Functional Theory (DFT) in a computationally efficient manner. We introduce a novel approach to modeling angular information between sets of neighboring atoms in a graph neural network. Results are demonstrated on the large-scale Open Catalyst 2020 dataset.
  arXiv  Detail & Related papers  (2021-06-17T14:59:34Z)
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities [4.2572103161049055]
  We introduce general SE(3)-equivariant operations and building blocks for constructing deep learning architectures for geometric point cloud data. Our model reduces prediction errors by up to two orders of magnitude compared to the previous state-of-the-art. We demonstrate the potential of our approach in a transfer learning application, where a model trained on low accuracy reference wavefunctions implicitly learns to correct for electronic many-body interactions.
  arXiv  Detail & Related papers  (2021-06-04T08:57:46Z)
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations [86.41674945012369]
  We develop a scalable and expressive Graph Neural Networks model, ForceNet, to approximate atomic forces. Our proposed ForceNet is able to predict atomic forces more accurately than state-of-the-art physics-based GNNs.
  arXiv  Detail & Related papers  (2021-03-02T03:09:06Z)
• Variational Monte Carlo calculations of $\mathbf{A\leq 4}$ nuclei with an artificial neural-network correlator ansatz [62.997667081978825]
  We introduce a neural-network quantum state ansatz to model the ground-state wave function of light nuclei. We compute the binding energies and point-nucleon densities of $Aleq 4$ nuclei as emerging from a leading-order pionless effective field theory Hamiltonian.
  arXiv  Detail & Related papers  (2020-07-28T14:52:28Z)
• Graph Neural Network for Hamiltonian-Based Material Property Prediction [56.94118357003096]
  We present and compare several different graph convolution networks that are able to predict the band gap for inorganic materials. The models are developed to incorporate two different features: the information of each orbital itself and the interaction between each other. The results show that our model can get a promising prediction accuracy with cross-validation.
  arXiv  Detail & Related papers  (2020-05-27T13:32:10Z)
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles [3.0980025155565376]
  "MuML" models are fitted together to reproduce molecular $boldsymbolmu$ computed using high-level coupled-cluster theory. We demonstrate that the uncertainty in the predictions can be estimated reliably using a calibrated committee model.
  arXiv  Detail & Related papers  (2020-03-27T14:35:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.