Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems

• URL: http://arxiv.org/abs/2106.02549v1
• Date: Fri, 4 Jun 2021 15:28:27 GMT
• Title: Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems
• Authors: Thorben Frank and Stefan Chmiela
• Abstract summary: We propose a variant to describe geometric relations for arbitrary atomic configurations in Euclidean space. We demonstrate how the successive application of our learned attention matrices effectively translates the molecular geometry into a set of individual atomic contributions on-the-fly.
• Score: 0.4351216340655199
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Attention mechanisms are developing into a viable alternative to convolutional layers as elementary building block of NNs. Their main advantage is that they are not restricted to capture local dependencies in the input, but can draw arbitrary connections. This unprecedented capability coincides with the long-standing problem of modeling global atomic interactions in molecular force fields and other many-body problems. In its original formulation, however, attention is not applicable to the continuous domains in which the atoms live. For this purpose we propose a variant to describe geometric relations for arbitrary atomic configurations in Euclidean space that also respects all relevant physical symmetries. We furthermore demonstrate, how the successive application of our learned attention matrices effectively translates the molecular geometry into a set of individual atomic contributions on-the-fly.

Related papers

• Cartesian atomic cluster expansion for machine learning interatomic potentials [0.0]
  Machine learning interatomic potentials are revolutionizing atomistic modelling in material science and chemistry. We propose a Cartesian-coordinates-based atomic density expansion that exhibits good accuracy, stability, and generalizability. We validate its performance in diverse systems, including bulk water, small molecules, and 25-element high-entropy alloys.
  arXiv  Detail & Related papers  (2024-02-12T08:17:23Z)
• Exploiting Hierarchical Interactions for Protein Surface Learning [52.10066114039307]
  Intrinsically, potential function sites in protein surfaces are determined by both geometric and chemical features. In this paper, we present a principled framework based on deep learning techniques, namely Hierarchical Chemical and Geometric Feature Interaction Network (HCGNet) Our method outperforms the prior state-of-the-art method by 2.3% in site prediction task and 3.2% in interaction matching task.
  arXiv  Detail & Related papers  (2024-01-17T14:10:40Z)
• A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems [87.30652640973317]
  Recent advances in computational modelling of atomic systems represent them as geometric graphs with atoms embedded as nodes in 3D Euclidean space. Geometric Graph Neural Networks have emerged as the preferred machine learning architecture powering applications ranging from protein structure prediction to molecular simulations and material generation. This paper provides a comprehensive and self-contained overview of the field of Geometric GNNs for 3D atomic systems.
  arXiv  Detail & Related papers  (2023-12-12T18:44:19Z)
• Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning [57.670845619155195]
  We introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA) ASBA addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information. Our method offers a more comprehensive way to learn representations for molecular property prediction and has broad potential in drug and material discovery applications.
  arXiv  Detail & Related papers  (2023-05-22T00:56:00Z)
• Completeness of Atomic Structure Representations [0.0]
  We present a novel approach to construct descriptors of emphfinite correlations based on the relative arrangement of particle triplets. Our strategy is demonstrated on a class of atomic arrangements that are specifically built to defy a broad class of conventional symmetric descriptors.
  arXiv  Detail & Related papers  (2023-02-28T17:11:42Z)
• Unified theory of atom-centered representations and graph convolutional machine-learning schemes [0.0]
  atom-centered density correlations (ACDC) are used as a basis for a body-ordered, symmetry-adapted expansion of the targets. We generalize ACDC to include multi-centered information, generating representations that provide a complete linear basis to regress symmetric functions of atomic coordinates.
  arXiv  Detail & Related papers  (2022-02-03T12:56:22Z)
• Geometric Transformer for End-to-End Molecule Properties Prediction [92.28929858529679]
  We introduce a Transformer-based architecture for molecule property prediction, which is able to capture the geometry of the molecule. We modify the classical positional encoder by an initial encoding of the molecule geometry, as well as a learned gated self-attention mechanism.
  arXiv  Detail & Related papers  (2021-10-26T14:14:40Z)
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties [0.0]
  We discuss a family of structural descriptors that generalize the very successful atom-centered density correlation features to the N-centers case. We show in particular how this construction can be applied to efficiently learn the matrix elements of the (effective) single-particle Hamiltonian written in an atom-centered orbital basis.
  arXiv  Detail & Related papers  (2021-09-24T17:19:57Z)
• Programmable Interactions and Emergent Geometry in an Atomic Array [0.0]
  Nonlocal interactions govern the flow of information and the formation of correlations in quantum systems. We report on the realization of programmable nonlocal interactions in an array of atomic ensembles within an optical cavity. Our work opens broader prospects for simulating frustrated magnets and topological phases, investigating quantum optimization algorithms, and engineering new entangled resource states for sensing and computation.
  arXiv  Detail & Related papers  (2021-06-08T03:00:49Z)
• The role of feature space in atomistic learning [62.997667081978825]
  Physically-inspired descriptors play a key role in the application of machine-learning techniques to atomistic simulations. We introduce a framework to compare different sets of descriptors, and different ways of transforming them by means of metrics and kernels. We compare representations built in terms of n-body correlations of the atom density, quantitatively assessing the information loss associated with the use of low-order features.
  arXiv  Detail & Related papers  (2020-09-06T14:12:09Z)
• 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)

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.